Communication method and communication apparatus

Abstract

A communication method and a communication apparatus, which are applied to positioning scenarios. The method comprises: receiving configuration information from a core network element; and processing a channel measurement result by using a first model, so as to obtain a probability distribution of measurement results of a measurement quantity used for positioning a terminal device, wherein the first model is determined on the basis of a configuration parameter of a generative model, and the configuration information is used for indicating the configuration parameter of the generative model, and the measurement quantity corresponds to the channel measurement result. In the solution of the present application, a core network element and a first device align configuration information of a generative model to obtain a fitted / trained first model for terminal device positioning, so that the improvement of the measurement precision of the terminal device is expected to be supported.

Description

Communication method and communication device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on December 12, 2023, with application number 202311710770.0, and invention name “A Communication Method and Communication Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and more particularly, to a communication method and a communication device. Background Art

[0003] In artificial intelligence (AI)-based positioning technologies, AI positioning models can be deployed in different devices or nodes. For example, they are typically deployed on the positioning device side, such as the location management function (LMF), or on the base station (gNodeB, gNB) side. The AI ​​positioning model uses channel measurement results reported by channel measurement network elements as input and outputs the location of the terminal device (e.g., user equipment (UE)). Therefore, the channel measurement network element typically needs to report channel measurement reports to the location management function network element.

[0004] In downlink positioning, the gNB sends a positioning reference signal (PRS) to the UE. The UE measures the PRS sent by the gNB and derives a Gaussian mixture model of the downlink received reference signal time difference (DL-RSTD) distribution. The UE then sends the relevant parameters of this Gaussian mixture model to core network elements (such as the LMF) for use in UE positioning. Research has found that current UE positioning accuracy is poor. Therefore, improving UE positioning accuracy is an urgent issue. Summary of the Invention

[0005] The present application provides a communication method and a communication device to support the improvement of the positioning accuracy of terminal equipment.

[0006] In a first aspect, a communication method is provided. The method may be executed by a first device, or may be executed by a chip or circuit of the first device, which is not limited in this application. For ease of description, the method is described below using the first device as an example.

[0007] The method includes: receiving configuration information from a core network element, the configuration information being used to indicate configuration parameters of a generation model; processing channel measurement results using a first model to obtain a probability distribution of measurement results of measurement quantities used for terminal device positioning; wherein the first model is determined based on the configuration parameters of the generation model, and the measurement quantities correspond to the channel measurement results.

[0008] According to the solution provided in the present application, the terminal device receives configuration information from the core network network element, so that the core network network element and the first device generate the configuration information of the model by aligning, and can obtain that the first model fitted / trained for terminal device positioning is the same, and then the analysis and application of the probability distribution of the measurement results of the measurement quantity based on the first model are more accurate, which can also improve the positioning accuracy of the terminal device.

[0009] Exemplarily, the channel measurement result is based on measurement of a reference signal. For example, the first device or other devices may measure the reference signal to obtain the channel measurement result.

[0010] Exemplarily, the first device may be a terminal device or an access network device. The first device may also be referred to as a network element that performs channel measurement, or a channel measurement network element, or a reference signal measurement node, etc., and this application does not limit the names thereof. The core network network element may be a positioning node or positioning device for managing the location of the terminal device, such as a location management function network element LMF.

[0011] In an embodiment of the present application, the first model is determined based on the configuration parameters of the generated model, which can be understood as: the first device can fit or train the first model according to the obtained configuration parameters of the generated model. If the generated model is a Gaussian mixture model, it means that the first device can train or fit a specific Gaussian mixture model or a specific type of Gaussian mixture model according to the configuration parameters, that is, at this time the first model is a trained Gaussian mixture model, which can be used for positioning the terminal device.

[0012] In an embodiment of the present application, the measurement quantity corresponds to the measurement result, which can be understood as follows: the first device measures one or more measurement quantities corresponding to the reference signal to obtain a measurement result, and the measurement result is the measurement result of the one or more measurement quantities. For example, taking the downlink positioning scenario as an example, assuming that the measurement quantity is the time difference of arrival (TDoA), the first device is a terminal device, network device #1 can send a reference signal to the terminal device, such as PRS#1, and network device #2 can send PRS#2 to the terminal device. Correspondingly, the terminal device can measure the TDoA of PRS#1 and PRS#2, such as t2-t1, which can be used as measurement result #1, where t1 represents the transmission time when network device #1 transmits signals to the terminal device, and t2 represents the transmission time when network device #2 transmits signals to the terminal device. Optionally, network device #1 and network device #2 can send PRS multiple times, or network device #3 can also send PRS #3 to the terminal device. Correspondingly, the terminal device can measure the TDoA of PRS #2 and PRS #3, for example, t3-t2, which can be used as measurement result #2, where t3 represents the transmission time when network device #3 transmits signals to the terminal device, and so on.

[0013] In combination with the first aspect, in some implementations of the first aspect, the method further includes: sending first information to a core network element, where the first information is used to indicate the probability distribution.

[0014] Based on the above scheme, the terminal device can send the first information to enable the core network network element to obtain the probability distribution of the measurement results of the measurement quantity used for terminal device positioning, and then accurately analyze the measurement quantity based on the probability distribution and the configuration information of the generated model, so as to facilitate high-precision positioning of the terminal device.

[0015] In combination with the first aspect, in some implementations of the first aspect, the method further includes: obtaining a type of the generated model and / or a function of the generated model.

[0016] Optionally, the type of the generation model and / or the function of the generation model may be dynamically configured to the first device by the core network element through signaling or messaging, or may be pre-configured, for example, the corresponding code, table or other method that can be used to indicate the type of the generation model and / or the function of the generation model may be pre-saved in the first device. This application does not limit the implementation method. For example, the first device may determine that the generation model that needs to be trained or fitted is a GMM through the type of the generation model and / or the function of the generation model, and locate the terminal device through the trained or fitted GMM (i.e., the first model).

[0017] In combination with the first aspect, in some implementations of the first aspect, the generative model is any one of the following: a Gaussian mixture model; a variational autoencoder; or a generative adversarial network.

[0018] In combination with the first aspect, in certain implementations of the first aspect, the generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: a generation method of the Gaussian mixture model; a convergence threshold of the Gaussian mixture model; a maximum number of iterations of the Gaussian mixture model; model parameters of the Gaussian mixture model; the maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; the maximum value N of the expected value of a single Gaussian model included in the Gaussian mixture model, where N is a positive number; the maximum value A of the variance or covariance of a single Gaussian model included in the Gaussian mixture model, where A is a positive number; and the proportion of one or more single Gaussian models included in the Gaussian mixture model in the Gaussian mixture model.

[0019] In combination with the first aspect, in certain implementations of the first aspect, the generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: structural parameters of the variational autoencoder; the type of neural network used by the variational autoencoder; the input and / or output dimensions of the variational autoencoder; and the values ​​of the model parameters of the variational autoencoder.

[0020] Among them, the structural parameters of the variational autoencoder include one or more of the following: the number of neural network layers used by the variational autoencoder, the number of neurons contained in the neural network used by the variational autoencoder, parameters related to the input layer of the variational autoencoder, parameters related to the hidden layer, or parameters related to the output layer.

[0021] In combination with the first aspect, in some implementations of the first aspect, the measurement quantity includes one or more of the following: reference signal time difference (RSTD); time difference of arrival (TDoA); time of arrival (ToA); angle of arrival (AoA); line of sight (LOS) probability.

[0022] It should be understood that the RSTD, TDoA, ToA, AoA, and LoS probability described above can be considered as measurement quantities for a channel measurement. A channel can include one or more pathnames (e.g., a set of pathnames). For example, the LoS probability can be the average LoS probability of the line-of-sight identification results corresponding to all pathnames in a channel. The ToA estimation result can be the average of the arrival times corresponding to all pathnames in a channel. The AoA estimation result can be the average of the arrival angles corresponding to all pathnames in a channel, etc.

[0023] It should be noted that the measurement quantity in the embodiment of the present application may be one or more of the above-mentioned parameters, and correspondingly, the measurement result of the measurement quantity may also be one or more, and the probability distribution of the measurement result of the measurement quantity used for terminal device positioning may also be one or more. This application does not limit this.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: the values ​​of k expected values; the values ​​of k variances or covariances; the values ​​of the proportions of k single Gaussian models in the Gaussian mixture model; wherein the k expected values, k variances or covariances correspond one-to-one to the k single Gaussian models.

[0025] For example, the probability distribution of the Gaussian mixture model satisfies:

[0026] in, That is, the expectation, variance (or covariance) of each single Gaussian model, and the probability (or proportion) of occurrence in the Gaussian mixture model.

[0027] In combination with the first aspect, in some implementations of the first aspect, the generation model is a variational autoencoder, and the first information includes one or more of the following: values ​​of model parameters of the variational autoencoder; values ​​of the probability distribution output by the variational autoencoder.

[0028] In combination with the first aspect, in certain implementations of the first aspect, the channel measurement result is based on the measurement of a reference signal, including any one of the following: the first device is an access network device, and the channel measurement result is obtained based on a first channel measurement, and the first channel measurement includes: measuring a detection reference signal from a terminal device; or, the first device is a terminal device, and the channel measurement result is obtained based on a second channel measurement, and the second channel measurement includes: measuring a positioning reference signal or a channel state information reference signal from an access network device; or, the first device is a first terminal device, and the channel measurement result is obtained based on a third channel measurement, and the third channel measurement includes: measuring a side positioning reference signal from a second terminal device.

[0029] In combination with the first aspect, in some implementations of the first aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate the first configuration parameter, wherein the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate the correspondence between the first configuration parameter and the second configuration parameter.

[0030] In combination with the first aspect, in certain implementations of the first aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from a core network network element includes: receiving configuration information from a core network network element through a first signaling; wherein the configuration information of the first configuration parameter is carried in a first part of the first signaling, and the configuration information of the second configuration parameter is carried in a second part of the first signaling.

[0031] In combination with the first aspect, in certain implementations of the first aspect, receiving configuration information from a core network network element through a first signaling includes: receiving a first configuration parameter from the core network network element through a first part of the first signaling at a first moment, and receiving a second configuration parameter from the core network network element through a second part of the first signaling at a second moment; wherein the first moment and the second moment are the same, or the first moment and the second moment are different.

[0032] In a second aspect, a communication method is provided. The method may be executed by a core network element, or may be executed by a chip or circuit of the core network element, which is not limited in this application. For ease of description, the following description is based on an example of execution by a core network element.

[0033] The method includes: sending configuration information to a first device, the configuration information being used to indicate configuration parameters of a generation model; receiving first information from the first device, the first information indicating a probability distribution of measurement results of a measurement quantity used for terminal device positioning, the probability distribution being related to the configuration parameters of the generation model.

[0034] It should be understood that the measurement amount corresponds to a channel measurement result, and the channel measurement result is based on measurement of a reference signal. For example, the first device or other devices may measure the reference signal to obtain the channel measurement result.

[0035] According to the solution provided in the present application, the core network network element sends configuration information to the terminal device, so that the core network network element and the first device can align the configuration information of the generated model, and can obtain that the first model fitted / trained for terminal device positioning is the same, and then the analysis and application of the probability distribution of the measurement results of the measurement quantity based on the first model are more accurate, which can also improve the positioning accuracy of the terminal device.

[0036] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: determining the location of the terminal device according to the probability distribution of the measurement results of the measurement quantity and the configuration parameters of the generation model.

[0037] In combination with the second aspect, in some implementations of the second aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate the first configuration parameter, wherein the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate the correspondence between the first configuration parameter and the second configuration parameter.

[0038] In combination with the second aspect, in some implementations of the second aspect, the generative model is any one of the following: a Gaussian mixture model; a variational autoencoder; or a generative adversarial network.

[0039] In combination with the second aspect, in some implementations of the second aspect, the generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: a generation method of the Gaussian mixture model; a convergence threshold of the Gaussian mixture model; a maximum number of iterations of the Gaussian mixture model; model parameters of the Gaussian mixture model; the maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; the maximum value N of the expected value of a single Gaussian model included in the Gaussian mixture model, where N is a positive number; the maximum value A of the variance or covariance of a single Gaussian model included in the Gaussian mixture model, where A is a positive number; and the proportion of one or more single Gaussian models included in the Gaussian mixture model in the Gaussian mixture model.

[0040] In combination with the second aspect, in certain implementations of the second aspect, the generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: structural parameters of the variational autoencoder; the type of neural network used by the variational autoencoder; the input and / or output dimensions of the variational autoencoder; and the values ​​of the model parameters of the variational autoencoder.

[0041] Among them, the structural parameters of the variational autoencoder include one or more of the following: the number of neural network layers used by the variational autoencoder, the number of neurons contained in the neural network used by the variational autoencoder, parameters related to the input layer of the variational autoencoder, parameters related to the hidden layer, or parameters related to the output layer.

[0042] In combination with the second aspect, in some implementations of the second aspect, the measurement quantity includes one or more of the following: reference signal time difference RSTD; time difference of arrival TDoA; time of arrival ToA; angle of arrival AoA; and line-of-sight LoS probability.

[0043] In combination with the second aspect, in some implementations of the second aspect, the generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: the values ​​of k expected values; the values ​​of k variances or covariances; the values ​​of the proportions of k single Gaussian models in the Gaussian mixture model; wherein the k expected values, k variances or covariances correspond one-to-one to the k single Gaussian models.

[0044] In combination with the second aspect, in some implementations of the second aspect, the generation model is a variational autoencoder, and the first information includes one or more of the following: values ​​of model parameters of the variational autoencoder; values ​​of the probability distribution output by the variational autoencoder.

[0045] In combination with the second aspect, in certain implementations of the second aspect, the channel measurement result is based on the measurement of the reference signal, including any one of the following: the first device is an access network device, and the channel measurement result is obtained based on the first channel measurement, and the first channel measurement includes: measuring the detection reference signal from the terminal device; or, the first device is a terminal device, and the channel measurement result is obtained based on the second channel measurement, and the second channel measurement includes: measuring the positioning reference signal or the channel state information reference signal from the access network device; or, the first device is a first terminal device, and the channel measurement result is obtained based on the third channel measurement, and the third channel measurement includes: measuring the side positioning reference signal from the second terminal device.

[0046] In combination with the second aspect, in some implementations of the second aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate the first configuration parameter, wherein the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate the correspondence between the first configuration parameter and the second configuration parameter.

[0047] In combination with the second aspect, in certain implementations of the second aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from a core network network element includes: receiving configuration information from a core network network element through a first signaling; wherein the configuration information of the first configuration parameter is carried in the first part of the first signaling, and the configuration information of the second configuration parameter is carried in the second part of the first signaling.

[0048] In combination with the second aspect, in certain implementations of the second aspect, receiving configuration information from a core network network element through a first signaling includes: receiving a first configuration parameter from the core network network element through a first part of the first signaling at a first moment, and receiving a second configuration parameter from the core network network element through a second part of the first signaling at a second moment; wherein the first moment and the second moment are the same, or the first moment and the second moment are different.

[0049] The beneficial effects of the above-mentioned second aspect and certain implementation methods of the second aspect can be referred to the corresponding description of the first aspect, and will not be repeated here.

[0050] In a third aspect, a communication method is provided. The method may be executed by a first device, or may be executed by a chip or circuit of the first device, which is not limited in this application. For ease of description, the following description is based on an example of execution by the first device.

[0051] The method includes: obtaining configuration information, where the configuration information is used to indicate configuration parameters of a generation model; using a first model to process channel measurement results to obtain a probability distribution of measurement results of measurement quantities used for terminal device positioning, where the first model is determined based on the configuration parameters of the generation model, and the measurement quantities correspond to the channel measurement results.

[0052] Exemplarily, the channel measurement result is based on measurement of a reference signal. For example, the first device or other devices may measure the reference signal to obtain the channel measurement result.

[0053] According to the solution provided in the present application, the terminal device sends configuration information to the core network network element, so that the core network network element and the first device can align the configuration information of the generated model, and can obtain that the first model fitted / trained for terminal device positioning is the same, and then the analysis and application of the probability distribution of the measurement results of the measurement quantity based on the first model are more accurate, which can also improve the positioning accuracy of the terminal device.

[0054] In combination with the third aspect, in certain implementations of the third aspect, the method also includes: sending all or part of the first information and configuration information to the core network element, the first information is used to indicate the probability distribution, and the configuration information is used to indicate the configuration parameters of the generated model.

[0055] In combination with the third aspect, in certain implementations of the third aspect, the method further includes: obtaining a type of the generated model and / or a function of the generated model.

[0056] In combination with the third aspect, in some implementations of the third aspect, the generative model is any one of the following: a Gaussian mixture model; a variational autoencoder; or a generative adversarial network.

[0057] In combination with the third aspect, in certain implementations of the third aspect, the generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: a generation method of the Gaussian mixture model; a convergence threshold of the Gaussian mixture model; a maximum number of iterations of the Gaussian mixture model; model parameters of the Gaussian mixture model; the maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; the maximum value N of the expected value of a single Gaussian model included in the Gaussian mixture model, where N is a positive number; the maximum value A of the variance or covariance of a single Gaussian model included in the Gaussian mixture model, where A is a positive number; and the proportion of one or more single Gaussian models included in the Gaussian mixture model in the Gaussian mixture model.

[0058] In combination with the third aspect, in certain implementations of the third aspect, the generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: structural parameters of the variational autoencoder; the type of neural network used by the variational autoencoder; the input and / or output dimensions of the variational autoencoder; and the values ​​of the model parameters of the variational autoencoder.

[0059] Among them, the structural parameters of the variational autoencoder include one or more of the following: the number of neural network layers used by the variational autoencoder, the number of neurons contained in the neural network used by the variational autoencoder, parameters related to the input layer of the variational autoencoder, parameters related to the hidden layer, or parameters related to the output layer.

[0060] In combination with the third aspect, in some implementations of the third aspect, the measurement quantity includes one or more of the following: reference signal time difference RSTD; time difference of arrival TDoA; time of arrival ToA; angle of arrival AoA; and line-of-sight LoS probability.

[0061] In combination with the third aspect, in certain implementations of the third aspect, the generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: the values ​​of k expected values; the values ​​of k variances or covariances; the values ​​of the proportions of k single Gaussian models in the Gaussian mixture model; wherein the k expected values, k variances or covariances correspond one-to-one to the k single Gaussian models.

[0062] In combination with the third aspect, in some implementations of the third aspect, the generation model is a variational autoencoder, and the first information includes one or more of the following: values ​​of model parameters of the variational autoencoder; values ​​of the probability distribution output by the variational autoencoder.

[0063] In combination with the third aspect, in certain implementations of the third aspect, the channel measurement result is based on the measurement of a reference signal, including any one of the following: the first device is an access network device, and the channel measurement result is obtained based on a first channel measurement, and the first channel measurement includes: measuring a detection reference signal from a terminal device; or, the first device is a terminal device, and the channel measurement result is obtained based on a second channel measurement, and the second channel measurement includes: measuring a positioning reference signal or a channel state information reference signal from an access network device; or, the first device is a first terminal device, and the channel measurement result is obtained based on a third channel measurement, and the third channel measurement includes: measuring a side positioning reference signal from a second terminal device.

[0064] In combination with the third aspect, in certain implementations of the third aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate the first configuration parameter, wherein the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate the correspondence between the first configuration parameter and the second configuration parameter.

[0065] In combination with the third aspect, in certain implementations of the third aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from a core network element includes: receiving configuration information from a core network element through a first signaling; wherein the configuration information of the first configuration parameter is carried in a first part of the first signaling, and the configuration information of the second configuration parameter is carried in a second part of the first signaling.

[0066] In combination with the third aspect, in certain implementations of the third aspect, receiving configuration information from a core network network element through a first signaling includes: receiving a first configuration parameter from the core network network element through a first part of the first signaling at a first moment, and receiving a second configuration parameter from the core network network element through a second part of the first signaling at a second moment; wherein the first moment and the second moment are the same, or the first moment and the second moment are different.

[0067] The beneficial effects of the third aspect and certain implementation methods of the third aspect can be referred to the relevant description of the first aspect, and will not be repeated here.

[0068] In a fourth aspect, a communication method is provided. The method may be executed by a core network element, or may be executed by a chip or circuit of the core network element, which is not limited in this application. For ease of description, the following description is based on an example of execution by a core network element.

[0069] The method includes: receiving first information and all or part of configuration information from a first device, the first information indicating a probability distribution of measurement results of a measurement quantity used for terminal device positioning, the configuration information indicating configuration parameters of a generation model, and the probability distribution being related to the configuration parameters of the generation model.

[0070] It should be understood that the measurement amount corresponds to a channel measurement result, and the channel measurement result is based on measurement of a reference signal. For example, the first device or other devices may measure the reference signal to obtain the channel measurement result.

[0071] According to the solution provided in the present application, the core network network element receives configuration information from the terminal device, so that the core network network element and the first device can align the configuration information of the generated model, and can obtain that the first model fitted / trained for terminal device positioning is the same, and then the analysis and application of the probability distribution of the measurement results of the measurement quantity based on the first model are more accurate, which can also improve the positioning accuracy of the terminal device.

[0072] In combination with the fourth aspect, in certain implementations of the fourth aspect, the method further includes: determining the location of the terminal device based on the probability distribution of the measurement results of the measurement quantity and the configuration parameters of the generation model.

[0073] In combination with the fourth aspect, in certain implementations of the fourth aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate the first configuration parameter, wherein the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate the correspondence between the first configuration parameter and the second configuration parameter.

[0074] In combination with the fourth aspect, in some implementations of the fourth aspect, the generative model is any one of the following: a Gaussian mixture model; a variational autoencoder; or a generative adversarial network.

[0075] In combination with the fourth aspect, in certain implementations of the fourth aspect, the generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: a generation method of the Gaussian mixture model; a convergence threshold of the Gaussian mixture model; a maximum number of iterations of the Gaussian mixture model; model parameters of the Gaussian mixture model; the maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; the maximum value N of the expected value of a single Gaussian model included in the Gaussian mixture model, where N is a positive number; the maximum value A of the variance or covariance of a single Gaussian model included in the Gaussian mixture model, where A is a positive number; and the proportion of one or more single Gaussian models included in the Gaussian mixture model in the Gaussian mixture model.

[0076] In combination with the fourth aspect, in certain implementations of the fourth aspect, the generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: structural parameters of the variational autoencoder; the type of neural network used by the variational autoencoder; the input and / or output dimensions of the variational autoencoder; and the values ​​of the model parameters of the variational autoencoder.

[0077] Among them, the structural parameters of the variational autoencoder include one or more of the following: the number of neural network layers used by the variational autoencoder, the number of neurons contained in the neural network used by the variational autoencoder, parameters related to the input layer of the variational autoencoder, parameters related to the hidden layer, or parameters related to the output layer.

[0078] In combination with the fourth aspect, in certain implementations of the fourth aspect, the measurement quantity includes one or more of the following: reference signal time difference RSTD; time difference of arrival TDoA; time of arrival ToA; angle of arrival AoA; and line-of-sight LoS probability.

[0079] In combination with the fourth aspect, in certain implementations of the fourth aspect, the generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: the values ​​of k expected values; the values ​​of k variances or covariances; the values ​​of the proportions of k single Gaussian models in the Gaussian mixture model; wherein the k expected values, k variances or covariances correspond one-to-one to the k single Gaussian models.

[0080] In combination with the fourth aspect, in some implementations of the fourth aspect, the generation model is a variational autoencoder, and the first information includes one or more of the following: the values ​​of the model parameters of the variational autoencoder; the values ​​of the probability distribution output by the variational autoencoder.

[0081] In combination with the fourth aspect, in certain implementations of the fourth aspect, the channel measurement result is based on the measurement of the reference signal, including any one of the following: the first device is an access network device, and the channel measurement result is obtained based on the first channel measurement, and the first channel measurement includes: measuring the detection reference signal from the terminal device; or, the first device is a terminal device, and the channel measurement result is obtained based on the second channel measurement, and the second channel measurement includes: measuring the positioning reference signal or the channel state information reference signal from the access network device; or, the first device is a first terminal device, and the channel measurement result is obtained based on the third channel measurement, and the third channel measurement includes: measuring the side positioning reference signal from the second terminal device.

[0082] In combination with the fourth aspect, in certain implementations of the fourth aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate the first configuration parameter, wherein the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate the correspondence between the first configuration parameter and the second configuration parameter.

[0083] In combination with the fourth aspect, in certain implementations of the fourth aspect, the configuration parameters include a first configuration parameter and a second configuration parameter, and receiving configuration information from a core network network element includes: receiving configuration information from a core network network element through a first signaling; wherein the configuration information of the first configuration parameter is carried in a first part of the first signaling, and the configuration information of the second configuration parameter is carried in a second part of the first signaling.

[0084] In combination with the fourth aspect, in certain implementations of the fourth aspect, receiving configuration information from a core network network element through a first signaling includes: receiving a first configuration parameter from the core network network element through a first part of the first signaling at a first moment, and receiving a second configuration parameter from the core network network element through a second part of the first signaling at a second moment; wherein the first moment and the second moment are the same, or the first moment and the second moment are different.

[0085] The beneficial effects of the fourth aspect and certain implementation methods of the fourth aspect can be referred to the relevant description of the second aspect, which will not be repeated here.

[0086] In a fifth aspect, a communication device is provided, which includes: a transceiver unit for receiving configuration information from a core network network element, where the configuration information is used to indicate the configuration parameters of a generation model; a processing unit for processing the channel measurement results using a first model to obtain a probability distribution of the measurement results of the measurement quantity used for terminal device positioning, where the first model is determined based on the configuration parameters of the generation model, and the measurement quantity corresponds to the channel measurement result.

[0087] Exemplarily, the channel measurement result is based on measurement of a reference signal. For example, the first device or other devices may measure the reference signal to obtain the channel measurement result.

[0088] The transceiver unit may perform the reception and transmission processing in the aforementioned first aspect, and the processing unit of the communication device may perform other processing except the reception and transmission in the aforementioned first aspect.

[0089] In a sixth aspect, a communication device is provided, which includes: a transceiver unit for sending configuration information to a first device, the configuration information being used to indicate configuration parameters of a generation model; a processing unit for receiving first information from the first device, the first information indicating a probability distribution of measurement results of a measurement quantity used for positioning the terminal device, the probability distribution being related to the configuration parameters of the generation model.

[0090] The transceiver unit may perform the reception and transmission processing in the aforementioned second aspect, and the processing unit of the communication device may perform other processing except reception and transmission in the aforementioned second aspect.

[0091] In the seventh aspect, a communication device is provided, which includes: a processing unit for configuring information, where the configuration information is used to indicate the configuration parameters of the generation model; a transceiver unit for processing the channel measurement results using a first model to obtain a probability distribution of the measurement results of the measurement quantity used for terminal device positioning, the first model is determined based on the configuration parameters of the generation model, and the measurement quantity corresponds to the channel measurement result.

[0092] Optionally, the channel measurement result is based on measurement of a reference signal. For example, the first device or other devices may measure the reference signal to obtain the channel measurement result.

[0093] The transceiver unit can perform the reception and transmission processing in the aforementioned third aspect, and the processing unit of the communication device can perform other processing except reception and transmission in the aforementioned third aspect.

[0094] In an eighth aspect, a communication device is provided, comprising: a transceiver unit for receiving all or part of first information and configuration information from a first device, the first information indicating a probability distribution of measurement results of a measurement quantity used for positioning the terminal device, the configuration information being used to indicate configuration parameters of a generation model, and the probability distribution being related to the configuration parameters of the generation model; and a processing unit for determining the position of the terminal device based on the probability distribution of the measurement results of the measurement quantity and the configuration parameters of the generation model.

[0095] The transceiver unit can perform the reception and transmission processing in the aforementioned fourth aspect, and the processing unit of the communication device can perform other processing except reception and transmission in the aforementioned fourth aspect.

[0096] In a ninth aspect, a communication device is provided, comprising a processing circuit for executing a computer program so that the device executes the method of the first to fourth aspects above and any possible implementation thereof.

[0097] Optionally, the processing circuit is one or more processors, or all or part of the circuits in one or more processors used for processing functions.

[0098] Optionally, the communication device further includes a memory, which is used to store the computer program, and the memory is one or more.

[0099] Optionally, the memory may be integrated with the processor, or the memory may be set separately from the processor, or the memory may be located within the processor.

[0100] Optionally, the communication device further includes a transceiver circuit, such as a transceiver or an input-output circuit.

[0101] In the tenth aspect, a communication system is provided, including: a first device and a core network network element, the first device is used to execute the method in the above-mentioned first aspect or third aspect and any possible implementation thereof, and the core network network element is used to execute the method in the above-mentioned second aspect or fourth aspect and any possible implementation thereof.

[0102] In the eleventh aspect, a computer-readable storage medium is provided, which stores a computer program or code. When the computer program or code is run on a computer, the computer executes the method in the above-mentioned first aspect or second aspect and any possible implementation thereof.

[0103] In the twelfth aspect, a chip is provided, comprising a processing circuit for running a computer program so that a device equipped with the chip executes the methods in the above-mentioned first to fourth aspects and any possible implementation thereof.

[0104] The chip may include an output circuit or interface for sending information or data, and an input circuit or interface for receiving information or data.

[0105] In a thirteenth aspect, a computer program product is provided, comprising: a computer program code, which, when the computer program code is run on the computer, executes the method in the above-mentioned first to fourth aspects and any possible implementation thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0106] FIG1 is a schematic diagram of a wireless communication system 100 applicable to an embodiment of the present application;

[0107] FIG2 is a schematic diagram of a wireless communication system 200 applicable to an embodiment of the present application;

[0108] FIG3 is a schematic diagram of a wireless communication system 300 applicable to an embodiment of the present application;

[0109] FIG4 is a schematic diagram of a network element involved in an embodiment of the present application;

[0110] Figure 5 is a schematic diagram of an AI / ML network element or module;

[0111] FIG6 is a schematic diagram of an AI positioning model framework;

[0112] FIG7 is a schematic diagram of TDoA positioning;

[0113] Figure 8 is a schematic diagram of LOS and NLOS;

[0114] FIG9 is a schematic diagram showing the probability distribution of Gaussian mixture models corresponding to different model fitting configurations;

[0115] FIG10 is a schematic flow chart of a communication method 1000 provided in an embodiment of the present application;

[0116] FIG11 is a schematic flow chart of a communication method 1100 provided in an embodiment of the present application;

[0117] FIG12 is a schematic flow chart of a communication method 1200 provided in an embodiment of the present application;

[0118] FIG13 is a schematic flow chart of a communication method 1300 provided in an embodiment of the present application;

[0119] FIG14 is a schematic flow chart of a communication method 1400 provided in an embodiment of the present application;

[0120] FIG15 is a schematic flow chart of a communication method 1500 provided in an embodiment of the present application;

[0121] FIG16 is a schematic flow chart of a communication method 1600 provided in an embodiment of the present application;

[0122] FIG17 is a schematic flow chart of a communication method 1700 provided in an embodiment of the present application;

[0123] FIG18 is a schematic block diagram of a communication device 1800 provided in an embodiment of the present application;

[0124] FIG19 is a schematic block diagram of a communication device 1900 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0125] The technical solution in this application will be described below with reference to the accompanying drawings.

[0126] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems such as sixth generation mobile communication systems, or a fusion system of multiple systems. The technical solutions provided in this application can also be applied to device to device (D2D) communication, vehicle to everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0127] A device in a communication system can send a signal to another device or receive a signal from another device. The signal may include information, signaling, or data, etc. The device can also be replaced by an entity, a network entity, a communication device, a communication module, a node, a communication node, etc., and the present application is described using a device as an example. For example, a communication system may include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It can be understood that the terminal device / network device in the present application can be replaced by a first device, and execute the corresponding communication method in the present application with a core network network element (for example, a positioning device, which can be a location management function network element LMF).

[0128] The terminal devices in the embodiments of the present application include various devices with wireless communication functions, which can be used to connect people, objects, machines, etc. The terminal devices can be widely used in various scenarios, such as: cellular communication, D2D, V2X, peer to peer (P2P), M2M, MTC, IoT, virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery, etc. The terminal device can be a terminal in any of the above scenarios, such as an MTC terminal, an IoT terminal, etc. The terminal device may be a user equipment (UE) of the third generation partnership project (3GPP) standard, a terminal, a fixed device, a mobile station device or a mobile device, a subscriber unit, a handheld device, a vehicle-mounted device, a wearable device, a cellular phone, a smart phone, a session initialization protocol (SIP) phone, a wireless data card, a personal digital assistant (PDA), a computer, a tablet computer, a notebook computer, a wireless modem, a handheld device (handset), a laptop computer, a computer with wireless transceiver function, a smart book, a vehicle, a satellite, a global positioning system (GPS) device, a target tracking device, an aircraft (such as a drone, a helicopter, a multi-copter, a quadcopter, or an airplane), a ship, a remote control device, a smart home device, an industrial device, or a device built into the above-mentioned device (such as a communication module, a modem or a chip in the above-mentioned device), or other processing devices connected to a wireless modem. For the sake of convenience of description, the terminal device will be described below by taking the terminal or UE as an example.

[0129] It should be understood that in some scenarios, a UE can also be used to act as a base station. For example, a UE can act as a scheduling entity that provides sidelink signals between UEs in scenarios such as V2X, D2D, or P2P.

[0130] In the embodiments of the present application, the device for implementing the function of the terminal device can be the terminal device, or it can be a device that can support the terminal device to implement the function, such as a chip system or chip, which can be installed in the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0131] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station may broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, RAN intelligent controller (RIC), etc. A base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. A base station may also refer to a communication module, modem, or chip used to be set in the aforementioned device or apparatus. A base station may also be a mobile switching center and a device that performs base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. A base station may support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by network devices.

[0132] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0133] In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0134] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0135] The RAN node may support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0136] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0137] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0138] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, the radio access network may also be an open radio access network (O-RAN) architecture. In the ORAN system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0139] In the embodiments of the present application, the device for implementing the function of the network device can be the network device, or it can be a device that can support the network device to implement the function, such as a chip system or chip, which can be installed in the network device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0140] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on the water surface; they can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which network devices and terminal devices are located. In addition, terminal devices and network devices can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of terminal devices and network devices.

[0141] In the embodiments of the present application, the location management function network element may be a positioning node or positioning device, such as an LMF, for performing location management on the terminal device. Exemplarily, the apparatus for locating or managing the terminal device's location may be the location management function network element, or may be a chip system, chip, or circuit of the location management function network element, which may be installed in the location management function network element. The chip system may consist of a chip alone, or may include a chip and other discrete components.

[0142] Optionally, the location management function network element may be a core network device, which refers to a device in the core network (CN) that provides service support for terminal devices. The core network device may include one or more core network elements. Taking the 5G core network as an example, the 5G core network includes an access and mobility management function (AMF) network element responsible for services such as mobility management and access management, a session management function (SMF) network element responsible for session management, a user plane function (UPF) network element responsible for data packet routing and forwarding and quality of service (QoS) control on the user plane, and a policy control function (PCF) network element. The above-mentioned core network elements may work independently or be combined to implement certain control functions. For example, the AMF, SMF, and PCF may be combined as a core network device. All or part of the above-mentioned core network elements may be independent in form or integrated into the same device, which is not limited here.

[0143] In an embodiment of the present application, the first device may be a terminal device or a network device, or a component of a terminal device or a network device (such as a chip or circuit). Optionally, the network device may be a network device provided with one or more AI modules. For example, the network device may be a core network device, an access network node (RAN node), or one or more devices in OAM. For example, the AI ​​module may be a RAN intelligent controller (RIC), such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is set in a RAN node (for example, in a CU or DU), and the non-real-time RIC is set in an OAM, a cloud server, a core network device, or other network devices. The location management function network element is a network element for training an AI positioning model and / or a storage network element for an AI positioning model library, or is also a selection / inference network element for an AI positioning model, for example, the AI ​​positioning model used for positioning is configured in the location management function network element.

[0144] Exemplarily, the first device and the location management function network element may be logically deployed separately. As different implementation methods, the first device and the location management function network element may be physically deployed in the same network element or different network elements, without limitation. For example, the first device is a terminal device, the location management function network element is a server (also called a host) or a cloud device in an over the top (OTT) system, and the terminal device and the server or cloud device of the OTT system can communicate through the Internet. For another example, the first device is a module in the terminal device (for example, a module of the physical layer), and the location management function network element is another module of the device (such as LMF) (for example, a module of the application layer, such as an application module connected to the OTT server). It can be understood that in the embodiments of the present application, the module can be implemented by hardware, or by software, or by a combination of hardware and software, without limitation.

[0145] First, a communication system applicable to the embodiments of the present application is briefly introduced as follows.

[0146] Figure 1 is a schematic diagram of a wireless communication system 100 applicable to an embodiment of the present application. As shown in Figure 1, the wireless communication system includes a wireless access network 100. The wireless access network 100 can be a next-generation (e.g., 6G or higher) wireless access network, or a traditional (e.g., 5G, 4G, 3G, or 2G) wireless access network. One or more terminal devices (120a-120j, collectively referred to as 120) can be connected to each other or to one or more network devices (110a, 110b, collectively referred to as 110) in the wireless access network 100. Figure 1 is only a schematic diagram, and the wireless communication system may also include other devices, such as core network devices, wireless relay devices, and / or wireless backhaul devices, which are not shown in Figure 1.

[0147] In practical applications, the wireless communication system may include multiple network devices and multiple terminal devices simultaneously, without limitation. A network device may serve one or more terminal devices simultaneously. A terminal device may also access one or more network devices simultaneously. The embodiments of the present application do not limit the number of terminal devices and network devices included in the wireless communication system.

[0148] Figure 2 is a schematic diagram of a wireless communication system 200 applicable to an embodiment of the present application. As shown in Figure 2 , the wireless communication system 200 may include at least one network device, such as the network device 210 shown in Figure 2 . The wireless communication system 200 may also include at least one terminal device, such as the terminal device 220 and the terminal device 230 shown in Figure 2 . The wireless communication system 200 may also include a positioning device, such as the positioning device 240 shown in Figure 2 . Exemplarily, positioning device 240 is a location management function (LMF) network element, hereinafter referred to as LMF.

[0149] The positioning device and the network device can communicate via interface messages. For example, if network device 210 is a gNB and positioning device 240 is a LMF, the gNB and LMF can exchange information via NRPPa messages. For another example, if network device 210 is an eNB and positioning device 240 is a LMF, the eNB and LMF can exchange information via LTE Positioning Protocol (LPP) messages.

[0150] The terminal device and the positioning device may communicate directly or through other devices, such as network devices and / or core network elements. As an example, as shown in FIG2 , the terminal device 220 and the positioning device 240 may communicate through the network device 210.

[0151] Optionally, the positioning device and the network device may be different modules of the same device, or may be separate and different devices.

[0152] Figure 3 is a schematic diagram of a wireless positioning system applicable to an embodiment of the present application. As shown in Figure 3, the wireless positioning system primarily includes an access network device, a terminal device, and a positioning device. The positioning device is primarily responsible for receiving positioning service requests, collecting positioning-related measurement results, calculating positioning results, and providing corresponding wireless positioning services. Optionally, the positioning device can receive positioning service requests from an access network device or an upper-layer application. As an example, the positioning device can be a location management function network element, such as an LMF. For information on the access network device and the terminal device, see the above description.

[0153] Figure 4 is a schematic diagram of a device involved in an embodiment of the present application. As shown in Figure 4, it includes a UE, a location management function network element, and an access network device. Optionally, it also includes an access mobility management function (AMF) network element. As an example, the access network device may be an ng-eNB or a gNB, where ng-eNB represents a 4G base station that can access the 5G core network, and gNB represents a 5G base station. Both are NR-RAN network elements. The radio access network device or base station mentioned in the embodiments of the present application may be an ng-eNB or a gNB, without limitation. The UE and the radio access network device communicate via corresponding interfaces. For example, the UE and gNB communicate via the NR-Uu interface, and the UE and ng-eNB communicate via the LTE-Uu interface. In the embodiments of the present application, the NR-Uu interface and the LTE-Uu interface are used to transmit positioning-related signaling and / or data. In addition, the gNB and the AMF, and the ng-eNB and the AMF, communicate via the NG-C interface, such as to transmit positioning-related signaling. AMF and LMF communicate with each other through the NL1 interface, such as transmitting positioning-related signaling. Optionally, the interaction between UE and LMF is based on the LTE positioning protocol (LPP) protocol, and the interaction between NG-RAN and LMF is based on the NRPPa protocol, and the NRPPa protocol is transparently transmitted across AMF. It should be understood that NG-RAN is only used as an example. When the technical solution of the present application is applied to future wireless communication systems, such as 6G systems, NG-RAN is correspondingly the access network device in the 6G system. Similarly, the names of the network elements, the names of the interfaces between the network elements, and the message names are only used as examples. In future wireless communication systems, network elements, interfaces, and interface messages with the same or similar functions can be used to implement the technical solution of the present application.

[0154] In addition, in order to support machine learning functions in wireless communication systems, AI nodes may also be introduced into wireless communication systems.

[0155] Optionally, the communication system also includes at least one AI node.

[0156] Optionally, the AI ​​node is deployed in one or more of the following: a network device, a terminal device, a core network, or a positioning device; or the AI ​​node may be deployed separately, such as in a location other than any of the aforementioned devices. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: a network device, a terminal device, a core network element, or a positioning device.

[0157] Optionally, the AI ​​node is used to perform AI-related operations. As an example, the AI-related operations may include one or more of: model failure testing, model performance testing, model training testing, or data collection.

[0158] For example, a network device may forward data related to an AI positioning model reported by a terminal device to an AI node, which may then perform AI-related operations. For another example, an access network device or a terminal device may forward data related to an AI positioning model to an AI node, which may then perform AI-related operations. For another example, an AI node may send the output of an AI-related operation, such as one or more of a trained neural network model, model evaluation, or test results, to a network device and / or a terminal device. For example, an AI node may directly send the output of an AI-related operation to a network device and a terminal device. For another example, an AI node may send the output of an AI-related operation to a terminal device via a network device. For another example, an AI node may send the output of an AI-related operation to a network device via a terminal device.

[0159] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0160] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0161] Exemplarily, the AI ​​node may be an AI network element or an AI module.

[0162] Figure 5 is a schematic diagram of an AI / ML network element or module. Among them, if an AI network element is introduced, it means that the AI ​​network element corresponds to an independent network element; if an AI module is introduced, the AI ​​module can be located inside a certain network element. As described above, the network elements involved in the embodiments of the present application include UE, wireless access network equipment and LMF, and optionally, AMF. An AI module can be set inside one or more of these UEs, wireless access network equipment, AMF (if the network element is involved) and LMF, or one or more of the UEs, wireless access network equipment, AMF and LMF introduce corresponding AI network elements, or a combination of these two methods, which is not limited in this application.

[0163] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements can be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of input parameters), hidden layer parameters (such as the type of hidden layer parameters and / or the dimension of hidden layer parameters), or output parameters (such as the type of output parameters and / or the dimension of output parameters).

[0164] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0165] It should be understood that if one or more of the UE, radio access network device, AMF, and LMF introduces a corresponding AI network element, and the AI ​​operation is performed by the corresponding AI network element, the UE, radio access network device, AMF, or LMF needs to send information related to the AI ​​operation to the corresponding AI network element. For example, the LMF introduces a corresponding AI network element, and the AI ​​network element performs the inference operation of the AI ​​model. After the LMF receives the channel measurement report from the first device (such as the access network device or UE), the channel measurement result carried in the channel measurement report is sent to the corresponding AI network element. For another example, in uplink positioning, if the access network device introduces the corresponding AI network element, it is assumed that the input of the AI ​​model is the channel feature extracted from the channel measurement result, and the channel measurement result is obtained by the access network device measuring the UE's sounding reference signal (SRS). Therefore, after obtaining the channel measurement result, the access network device sends the channel measurement result to the corresponding AI network element, and the AI ​​network element extracts the channel feature from the channel measurement result through the AI ​​model, and then returns the extracted channel feature to the access network device, and then the access network device sends the channel feature to the LMF.

[0166] It can also be understood that Figures 1 to 5 are simplified schematic diagrams for ease of understanding. The wireless communication system may also include other network devices, or other terminal devices, or other AI nodes, which are not drawn in Figures 1 to 5.

[0167] To facilitate understanding of the embodiments of the present application, the following is a brief explanation of the terms involved in the embodiments of the present application.

[0168] (1) Artificial Intelligence (AI);

[0169] The goal is to give machines the ability to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, artificial intelligence refers to the technology that represents human intelligence through computer programs. The goals of artificial intelligence include understanding intelligence by constructing computer programs that can perform symbolic reasoning or deduction.

[0170] (2) Machine learning (ML);

[0171] ML is an implementation of artificial intelligence. Machine learning is a method that empowers machines to learn, enabling them to perform tasks that cannot be accomplished through direct programming. In practical terms, machine learning utilizes data to train models and then uses these models to make predictions. There are many machine learning methods, such as neural networks (NNs), decision trees, and support vector machines. Machine learning theory primarily focuses on the design and analysis of algorithms that enable computers to learn automatically. Machine learning algorithms automatically analyze data to identify patterns and use these patterns to make predictions about unknown data.

[0172] (3) AI models;

[0173] An AI model is an algorithm or computer program that can implement AI functions. An AI model represents the mapping relationship between the model's input and output. In other words, an AI model is a function model that maps inputs of a certain dimension to outputs of a certain dimension. The parameters of the function model can be obtained through machine learning training. For example, f(x) = mx 2 +n is a quadratic function model, which can be regarded as an AI model, and m and n are parameters of the AI ​​model, which can be obtained through machine learning training. For example, the AI ​​models mentioned in the embodiments below are not limited to neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q learning models, or other machine learning (ML) models.

[0174] AI model design primarily includes a data collection phase (e.g., collecting training data and / or inference data), a model training phase, and a model inference phase. It can also include an inference result application phase. In the aforementioned data collection phase, a data source is used to provide training data sets and inference data. In the model training phase, an AI model is obtained by analyzing or training the training data provided by the data source. Learning the AI ​​model through the model training node is equivalent to using the training data to learn the mapping relationship between the AI ​​model's input and output. In the model inference phase, the AI ​​model, trained in the model training phase, performs inference based on the inference data provided by the data source to obtain an inference result. This phase can also be understood as inputting the inference data into the AI ​​model and obtaining an output from the AI ​​model, which is the inference result. The inference result can indicate configuration parameters used (executed) by the execution object and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be centrally planned by an actor entity, such as an actor entity that sends the inference result to one or more actors (e.g., core network devices, access network devices, or terminal devices) for execution. For example, the execution entity can also provide feedback on the performance of the AI ​​model to the data source, facilitating subsequent update and training of the AI ​​model.

[0175] It is understood that the AI ​​model can be implemented as a hardware circuit, software, or a combination of software and hardware, without limitation. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application, or software application.

[0176] (4) Neural network (NN);

[0177] Neural networks are a specific implementation of AI or machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, giving them the ability to learn arbitrary mappings.

[0178] A neural network can be composed of neural units, which can be a computational unit that takes xs and an intercept 1 as input. A neural network is formed by connecting many of these single neural units, meaning that the output of one neural unit can be the input of another. The input of each neural unit can be connected to the local receptive field of the previous layer to extract features from that local receptive field, which can be an area consisting of several neural units.

[0179] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in this application can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN).

[0180] (5) Training data set and inference data;

[0181] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0182] A training dataset is used to train an AI model. It may include the input to the AI ​​model, or the input and target output of the AI ​​model. A training dataset includes one or more training data. Training data may include training samples input to the AI ​​model, or the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or labeled sample. A label is the true value.

[0183] In the communications field, training datasets can include simulated data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Because the geographical environments and channel conditions in which data are generated vary, such as indoor and outdoor locations, mobile speeds, frequency bands, or antenna configurations, the collected data can be categorized during acquisition. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0184] Model training essentially involves learning certain characteristics from training data. When training an AI model (such as a neural network), the goal is to ensure that the model's output is as close as possible to the desired predicted value. This is done by comparing the network's predictions with the desired target values. The weight vectors of each layer of the AI ​​model are then updated based on the difference between the two. (Of course, before the first update, there's usually an initialization process, which pre-configures the parameters for each layer of the AI ​​model.) For example, if the network's prediction is too high, the weight vectors are adjusted to predict a lower value. This adjustment is repeated until the AI ​​model predicts the desired target value, or a value very close to it. Therefore, it's necessary to predefine how to compare the difference between the predicted and target values. This is known as the loss function, or objective function. These are important equations used to measure the difference between the predicted and target values. For example, a higher loss function indicates a greater difference. Therefore, training an AI model becomes a process of minimizing this loss, keeping the loss function below a threshold or ensuring that the loss function meets the target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers, width, weights of neurons, or parameters in the activation function of neurons of the neural network.

[0185] Inference data can be used as input to a trained AI model for inference. During the inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0186] Figure 6 is an AI application framework.

[0187] In the aforementioned data collection phase, the data source is used to provide training datasets and inference data. In the model training phase, an AI model is obtained by analyzing or training the training data provided by the data source. The AI ​​model represents the mapping relationship between the model's input and output. Learning the AI ​​model through the model training node is equivalent to learning the mapping relationship between the model's input and output using the training data. In the model inference phase, the AI ​​model trained in the model training phase is used to perform inference based on the inference data provided by the data source, obtaining an inference result. This phase can also be understood as inputting the inference data into the AI ​​model and obtaining an output from the AI ​​model, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be centrally planned by the execution (actor) entity, for example, the execution entity can send the inference result to one or more execution objects (e.g., access network equipment or terminal devices) for execution. Alternatively, the execution entity can provide feedback on the model's performance to the data source to facilitate subsequent model update and training.

[0188] It is understandable that a communication system may include network elements with artificial intelligence capabilities. The above-mentioned AI model design-related steps can be performed by one or more network elements with artificial intelligence capabilities. In one possible design, AI functions (such as AI modules or AI entities) can be configured in existing network elements in the communication system to implement AI-related operations, such as AI model training and / or inference. For example, the existing network element can be an access network device or a terminal device. Alternatively, in another possible design, an independent network element can be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element can be referred to as an AI network element or an AI node, etc., and the embodiments of the present application are not limited to these names. For example, the AI ​​network element can be directly connected to the network equipment in the communication system, or it can be indirectly connected to the network equipment through a third-party network element. The third-party network element can be a core network element such as an authentication management function (AMF) network element, a user plane function (UPF) network element, an operation administration and maintenance (OAM) network element, a cloud server, or other network element, without limitation. Exemplarily, the independent network element may be deployed on one or more of the network device side, the terminal device side, or the core network side. Optionally, it may be deployed on a cloud server.

[0189] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The reasoning process of different models can be deployed in different devices or nodes, or in the same device or node. Exemplarily, the model parameters of the AI ​​model may include one or more of the following structural parameters of the model (such as the number of layers of the model, and / or weights, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0190] (6) Generative model;

[0191] A generative model is one that can randomly generate observations, typically given certain implicit parameters. In machine learning (ML), generative models can be used to directly model data (for example, sampling data based on the probability density function of a variable) or to construct conditional probability distributions across variables. These conditional probability distributions can be generated by generative models using Bayes' theorem.

[0192] For example, the data generation method for the generative model includes the following steps:

[0193] a) Obtaining a probability distribution model of training samples based on training sample data and a specific generative learning method;

[0194] b) performing data sampling on the obtained probability distribution model to obtain a newly generated data sample;

[0195] The generative model represents the distribution of data from a statistical perspective and can reflect the similarity of similar data itself.

[0196] For example, the generative model includes but is not limited to: Naive Bayes method, Markov model, Gaussian Mixture Model (GMM), and is generally based on statistics and Bayesian theory.

[0197] For another example, generative models based on deep learning concepts include, but are not limited to, variational autoencoders (VAEs) and generative adversarial networks (GANs). For ease of understanding and description, the technical solutions of this application are illustrated using GMM and VAE as generative models.

[0198] (7) Gaussian Mixture Model (GMM);

[0199] A GMM is a generative model that can be viewed as a combination of K single Gaussian models (also called sub-steps), where K is an integer greater than or equal to 1. These K single Gaussian models serve as the latent variables of the mixture model. Generally speaking, a mixture model can use any probability distribution. The Gaussian mixture model (GMM) is used here because of its favorable mathematical properties and good computational performance.

[0200] For example, the definition of a single Gaussian model can be: when the sample data X is one-dimensional data, the probability density function satisfied by the Gaussian distribution is as follows:

[0201] Among them, μ is the mean of the data, σ is the standard deviation of the data;

[0202] When the sample data X is multidimensional data, the probability density function satisfied by the Gaussian distribution is as follows:

[0203] Among them, μ is the mean of the data, Σ is the covariance of the data, and D is the dimension of the data.

[0204] For example, the probability distribution of the Gaussian mixture model GMM satisfies:

[0205] In general, the complete mixed Gaussian model includes the covariance matrix, parameter mean vector and mixing weight, which can be expressed as θ, that is, θ = (r k ,σ k ,p k ), r k , σ k 、p k They respectively represent the expectation (or mean), variance (or covariance), and probability of occurrence (which can be called weight) of the k-th single Gaussian model in the mixed model.

[0206] (8) Variational AutoEncoder (VAE);

[0207] A VAE is a generative model consisting of an encoder and a decoder that is trained to minimize the reconstruction error between the output data after passing through the encoder and decoder and the initial input data. Optionally, to introduce some regularization of the latent space, the VAE can modify the encoding-decoding process, encoding the input data as a probability distribution in the latent space rather than a single point in the latent space. This is achieved by:

[0208] a) Encode the input as a distribution in the latent space;

[0209] b) Sample a point in the latent space from this distribution;

[0210] c) decoding the sampling points and calculating the reconstruction error;

[0211] d) The reconstruction error is back-propagated through the network.

[0212] It should be noted that after encoding by the variational autoencoder, the feature of each measurement result is no longer a single value in the variational autoencoder but a probability distribution. VAE can use two neural networks to establish two probability density distribution models: one is used for variational inference of the original input data, that is, to generate the variational probability distribution of the latent variables, which is called the inference network; the other is used to restore the approximate probability distribution of the original data based on the variational probability distribution of the generated latent variables, which is called the generation network.

[0213] (9) Generative Adversarial Networks (GANs);

[0214] GANs are a typical unsupervised learning method that can automatically extract features and generate data. They consist of two key components: a generator (which generates data through a neural network) that creates data as similar as possible to the original data to deceive the discriminator; and a discriminator (which uses a neural network to determine whether the data is real or machine-generated) that identifies "fake" data generated by the generator.

[0215] The essence of GANs is to leverage the powerful nonlinear fitting capabilities of neural networks to learn a nonlinear mapping from an arbitrary prior noise distribution to a real data distribution, thereby enabling the generator to produce realistic samples. The GAN input is an arbitrary noise distribution, and the final data is generated through supervision from the original training data.

[0216] (10) Expectation Maximization (EM) algorithm;

[0217] The EM algorithm is an iterative optimization strategy that can solve the parameter estimation problem in the case of missing data. Its basic idea is: first, estimate the value of the model parameters based on the given observation data; then estimate the value of the missing data based on the value of the model parameters; and then re-estimate the value of the model parameters based on the value of the missing data plus the given observation data. Repeat the iteration until convergence and the iteration ends.

[0218] (11) Time difference of arrival (TDoA): A positioning method that uses time difference.

[0219] Figure 7 is a schematic diagram of TDoA positioning. As shown in Figure 7, assume that the distance between network device #1 and the terminal device is d1, and the transmission time between network device #1 and the terminal device is t1; the distance between network device #2 and the terminal device is d2, and the transmission time between network device #2 and the terminal device is t2; and the distance between network device #3 and the terminal device is d3, and the transmission time between network device #3 and the terminal device is t3.

[0220] In TDoA, as an example, multiple network devices can send reference signals to the terminal device, such as a positioning reference signal (PRS), and the terminal device determines the location of the terminal device by measuring the TDoA of the reference signal, wherein the TDoA of the reference signal can also be called the reference signal time difference (RSTD). Taking Figure 7 as an example, it is assumed that the reference signal sent by network device #1 to the terminal device is P1, the reference signal sent by network device #2 to the terminal device is P2, and the reference signal sent by network device #3 to the terminal device is P3. The terminal device measures the TDoA of P2 and P1, that is, t2-t1, and uses t2-t1 to infer the distance difference d2-d1 between network device #2 and network device #1, and obtains a curve, each point on the curve satisfies the distance difference d2-d1 to network device #2 and network device #1. Similarly, the terminal device measures the TDoA of P3 and P1, i.e., t3 - t1. Using t3 - t1, the distance difference d3 - d1 between network device #3 and network device #1 can be inferred, resulting in another curve where every point on this curve satisfies the distance difference d3 - d1 to network device #3 and network device #1. The intersection of these two curves can be used to determine the terminal device's location, which can be expressed mathematically as shown in Formula (4):

[0221] Among them, (a i , b i) represents the location coordinates of network device #i. (a, b) represents the location coordinates of the terminal device to be determined. For example, a represents the location coordinates of the terminal device to be determined on the X-axis, b represents the location coordinates of the terminal device to be determined on the Y-axis, and c represents the speed of light.

[0222] Since there are certain synchronization errors between different network devices, the corresponding measurement values ​​also have certain uncertainties.

[0223] Figure 7 above describes a positioning method based on a reference signal sent by a network device to a terminal device. This method is also called downlink TDoA (DL-TDoA) or observed time difference of arrival (OTDoA). Similarly, positioning can also be performed by sending a reference signal, such as an SRS, from a terminal device to a network device. This positioning method is called uplink TDoA (UL-TDoA).

[0224] It is understood that in addition to measuring time difference, positioning can also be performed by measuring angles. The angle can be the angle of arrival (AoA) or the angle of departure (AoD). The angle of arrival is used to indicate the angle between the direction in which the receiving end receives the signal and a reference direction. The angle of departure is used to indicate the angle between the direction in which the transmitting end sends the signal and a reference direction, where the reference direction can be a direction determined based on the position and / or shape of the antenna.

[0225] In actual communication scenarios, due to the influence of noise and interference, there will be certain measurement errors in the time or angle measurements, and the corresponding positioning results will also have certain errors.

[0226] Figure 8 illustrates line-of-sight (LoS) and non-line-of-sight (NLoS) scenarios. As shown in Figure 8, the LoS between the network device and the terminal device (dashed line in Figure 8) is blocked by an obstruction. The reference signal transmitted between the network device and the terminal device is actually the reflected NLoS (solid line in Figure 8). As can be seen from the figure, the NLoS distance (i.e., d2 + d3) is greater than the LoS distance (i.e., d1). If NLoS is considered LoS when estimating position, significant measurement errors may occur. Therefore, LoS and NLoS classification is also important for positioning accuracy.

[0227] In AI-based positioning technologies, the AI ​​positioning model is typically deployed in the LMF. The AI ​​positioning model uses channel measurement results reported by the channel measurement network element as input and outputs the terminal device's location. Therefore, the channel measurement network element typically needs to report channel measurement reports to the location management function network element. For example, in downlink positioning, the gNB sends a public relay signal (PRS) to the UE. The UE measures the PRS sent by the gNB, obtains the GMM of the DL-RSTD distribution, and sends the relevant GMM parameters to the LMF for the LMF to locate the UE.

[0228] Figure 9 shows a schematic diagram of the probability distribution of the Gaussian mixture model (which can be called a Gaussian mixture distribution) corresponding to different model fitting configurations. Among them, Figure 9 (a) represents the true value of the Gaussian mixture distribution of the data, and the Gaussian mixture model includes 3 single Gaussian models. Specifically, Figure 9 (b) represents the Gaussian mixture distribution obtained by converging with a number of single Gaussian models of 2 and a maximum number of iterations of 10, Figure 9 (c) represents the Gaussian mixture distribution obtained by converging with a number of single Gaussian models of 2 and a maximum number of iterations of 50, and Figure 9 (d) represents the Gaussian mixture distribution obtained by converging with a number of single Gaussian models of 3 and a maximum number of iterations of 50. It can be seen that the more single Gaussian models and the greater the maximum number of iterations, the closer to the true value of the Gaussian mixture distribution. For the same Gaussian mixture distribution, the results obtained by converging using different model fitting configurations may be different, that is, the GMMs fitted by the UE using different model fitting configurations are quite different, which may lead to poor UE positioning accuracy. Therefore, how to improve the positioning accuracy of the UE is an urgent problem to be solved.

[0229] Based on this, an embodiment of the present application provides a communication method and a communication device. By aligning the configuration information of the generated model between the core network network element and the first device, it can be known that the first model fitted / trained for terminal device positioning is the same, and then the analysis and application of the probability distribution of the measurement results of the measurement quantity based on the first model are more accurate, which can also improve the positioning accuracy of the terminal device.

[0230] The communication method provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings. The embodiment provided by the present application can be applied to the communication system shown in Figure 1 or Figure 2 above, without limitation.

[0231] Figure 10 is a schematic flow chart of a communication method 1000 provided in an embodiment of the present application. As shown in Figure 10, method 1000 may include the following multiple steps. It should be understood that the method can be executed by the first device and the core network element, or it can also be executed by the chip, chip system or circuit of the first device and the core network element, and the present application does not limit this. For the convenience of description, the following example is taken as the execution subject. It should be noted that the training / fitting of the model in this implementation method occurs on the first device side, and the model reasoning / use occurs on the core network element side, or the training / fitting of the model occurs on the OTT or third-party device or cloud device side, and the model reasoning / use occurs on the OTT or third-party device or cloud device side, and the present application does not limit this.

[0232] S1010, a core network element sends configuration information to a first device, and correspondingly, the first device receives the configuration information from the core network element.

[0233] The configuration information is used to indicate the configuration parameters of the generated model.

[0234] In one example, the first device may be a terminal device or an access network device, and the core network element may be a positioning node or positioning device for managing the location of the terminal device, such as a location management function network element (such as an LMF). The first device may also be referred to as a network element that performs channel measurement, or a channel measurement network element, or a reference signal measurement node, etc., and this application does not limit these names.

[0235] Exemplarily, the generative model is any of the following:

[0236] (1) Gaussian mixture model GMM. For specific interpretation, please refer to the above description.

[0237] (2) Variational Autoencoder VAE. For specific explanation, please refer to the above description.

[0238] (3) Generative Adversarial Network (GAN). For its specific meaning, please refer to the above description.

[0239] In a first implementation, when the generative model is a GMM, the configuration parameters include one or more of the following:

[0240] (1) The maximum number of single Gaussian models contained in GMM is M, where M is a positive integer;

[0241] Exemplarily, the upper limit of the number of single Gaussian models included in the GMM is 5, which means that the number of single Gaussian models included in the GMM is less than or equal to 5, that is, M≤5. For example, the number of single Gaussian models included in the GMM can be 2 or 3.

[0242] (2) GMM generation method;

[0243] Exemplarily, the GMM generation method may be the EM algorithm, which is an iterative algorithm used for maximum likelihood estimation or maximum a posteriori probability estimation of a probability parameter model containing hidden variables. For example, the first device first estimates the values ​​of the model parameters based on the given observation data; then estimates the values ​​of the missing data based on the values ​​of the model parameters; and then re-estimates the values ​​of the model parameters based on the values ​​of the missing data plus the given observation data, and iterates repeatedly until convergence is achieved, and the iteration ends.

[0244] (3) GMM convergence threshold;

[0245] For example, assuming that the convergence threshold is p, it can be understood that the convergence value of the GMM obtained by training or fitting the first device is less than or equal to p, for example, p = 0.01. For example, the convergence value of the GMM obtained by training the first device is q, q is less than or equal to p, where both p and q are positive numbers.

[0246] (4) The maximum number of GMM iterations;

[0247] For example, if the upper limit of the number of iterations is 50, it means that during the training or fitting of the GMM by the first device, the number of iterations is less than or equal to 50. For example, the number of iterations can be 10, 20, or 50. It should be understood that, to a certain extent, the greater the number of iterations, the better the convergence effect.

[0248] (5) GMM model parameters;

[0249] Exemplarily, the model parameters of the GMM include one or more of the following: the expected r of the k single Gaussian models contained in the GMM k , the variance or covariance σ of k single Gaussian models k , the proportion of k single Gaussian models in GMM p k , for specific interpretation, please refer to the relevant description of the above formula (3).

[0250] (6) The maximum value N of the expected value of a single Gaussian model included in the GMM, where N is a positive number;

[0251] For example, assuming that the GMM includes three single Gaussian models, the expected values ​​of these three single Gaussian models are all less than or equal to N.

[0252] (7) The maximum value A of the variance or covariance of the single Gaussian model included in the GMM, where A is a positive number;

[0253] For example, assuming that the GMM includes three single Gaussian models, the variances or covariances of the three single Gaussian models are all less than or equal to A.

[0254] (8) The proportion of one or more single Gaussian models included in the GMM is X.

[0255] For example, assuming that the GMM includes three single Gaussian models, the proportion of these three single Gaussian models in the entire GMM is less than or equal to X.

[0256] In the second implementation, when the generative model is a VAE, the configuration parameters include one or more of the following:

[0257] (1) The values ​​of VAE model parameters;

[0258] The model parameters of the VAE include one or more of the following: neuron weights, neuron activation functions, or biases in neuron activation functions, where the bias in the activation function can also be referred to as the bias of the neural network. It should be understood that the model parameters of the VAE refer to pre-trained model parameters, i.e., the first device can determine a pre-trained VAE based on the model parameters of the VAE.

[0259] For example, suppose the input of a neuron is x = [x0, x1, ..., x n ], the corresponding weights are w=[w,w1,…,w n ], the bias of the weighted sum is b. Among them, b can be an integer, a decimal, or a complex number. The form of the activation function can be diverse. For example, if the activation function of a neuron is: y = f(z) = max(0,z), then the output of the neuron is: For another example, assuming that the activation function of a neuron is: y = f(z) = z, then the output of the neuron is: The activation functions of different neurons in a neural network can be the same or different.

[0260] (2) Structural parameters of VAE;

[0261] Exemplarily, the structural parameters of VAE include one or more of the following: the number of neural network layers used by VAE, the number of neurons contained in the neural network used by VAE, parameters related to the input layer of VAE, i.e., input parameters, parameters related to the hidden layer of VAE, or parameters related to the output layer of VAE, i.e., output parameters. For specific explanations, please refer to the description related to the above AI model.

[0262] It should be understood that the neural network used by VAE may include a multi-layer structure, and each layer may include one or more logic judgment units, which may be called neurons. For example, a neural network includes an input layer and an output layer. The input layer of the neural network processes the received input through neurons and passes the result to the output layer, and the output layer obtains the output result of the neural network. For another example, a neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the received input through neurons and passes the result to the middle hidden layer. The hidden layer then passes the calculation result to the output layer or the adjacent hidden layer, and finally the output layer obtains the output result of the neural network. A neural network may include one or more hidden layers connected in sequence, without limitation.

[0263] For example, the number of neural network layers used by VAE can be referred to as the depth of the neural network. Increasing the depth of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems.

[0264] For example, the neural network used by VAE includes a multi-layer structure, and the number of neurons in each layer can be called the width of the layer. Increasing the width of the neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems.

[0265] For example, the input dimension of a VAE can refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence can indicate the length of the sequence. The output dimension of a VAE can refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence can indicate the length of the sequence. In other words, VAE can represent the mapping relationship between the input and output of the model, or VAE is a function model that maps input of a certain dimension to output of a certain dimension.

[0266] (3) The type of neural network used by the VAE;

[0267] Exemplarily, the type of neural network used by VAE may be a deep neural network DNN or other neural networks, wherein DNN may include one or more of the following: a feedforward neural network FNN, a convolutional neural network CNN, or a recurrent neural network RNN.

[0268] It should be noted that this application does not specifically limit the number, transmission method, or transmission timing of configuration parameters. In addition, it is understood that configuration parameters not indicated may be predefined by the protocol or obtained in other ways, which are not limited here.

[0269] Optionally, the configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, the configuration information is used to indicate a portion (e.g., the first configuration parameter or the second configuration parameter), and the other configuration parameters can be determined based on a mapping relationship, wherein the mapping relationship is the corresponding relationship between the first configuration parameter and the second configuration parameter. This implementation method can save signaling overhead. In other words, the configuration information in the embodiments of the present application can indicate all configuration parameters of the generation model, or can indicate some configuration parameters of the generation model, and this application does not limit this.

[0270] In the present application, the mapping relationship between the first configuration parameter and the second configuration parameter can be predefined, and the predefinition can include pre-definition, such as protocol definition; or, the mapping relationship can be configured or pre-configured through signaling, and the pre-configuration can be implemented by pre-saving the corresponding code, table or other methods that can be used to indicate relevant information in the device. This application does not limit its specific implementation method.

[0271] Optionally, the mapping relationship can exist in the form of a table, function, text, or string, such as for storage or transmission.

[0272] Below, the mapping relationship between the first configuration parameter and the second configuration parameter is exemplified in table form. As shown in Table 1, taking GMM as an example, assuming that the configuration information is used to indicate the first configuration parameter, that is, the maximum number of single Gaussian models contained in the GMM is M = 5, and the GMM generation method is the EM algorithm, then according to the mapping relationship shown in Table 1, the convergence threshold p = 0.01 of the GMM and the maximum number of iterations of the GMM are 100 can also be determined. Based on these configuration parameters, a specific GMM can be fitted, namely the first model. Taking VAE as an example, assuming that the configuration information is used to indicate the second configuration parameter, that is, the number of neural network layers used by the VAE is 5 and the number of neurons contained in the neural network used by the VAE is 1, then according to the mapping relationship shown in Table 1, it can also be determined that the neural network used by the VAE is DNN. Based on these configuration parameters, a specific VAE can be fitted, namely the first model.

[0273] Optionally, this application does not limit the number of first configuration parameters and second configuration parameters corresponding to each generation model in Table 1.

[0274] Table 1

[0275] It should be understood that the mapping relationship between the first configuration parameter and the second configuration parameter of the GMM shown in Table 1 above, and the mapping relationship between the first configuration parameter and the second configuration parameter of the VAE, can be implemented independently or in combination. For example, a row corresponding to the GMM and a row corresponding to the VAE in Table 1 can be respectively reflected in two tables, and this application is not limited to this.

[0276] It should be understood that Table 1 above is merely an example provided for ease of understanding and should not constitute any limitation to the technical solution of the present application.

[0277] Optionally, the configuration parameters include a first configuration parameter and a second configuration parameter, and the first device receives configuration information from the core network network element, including: the first device receives the configuration information from the core network network element through the first signaling; wherein, the configuration information of the first configuration parameter is carried in the first part of the first signaling, and the configuration information of the second configuration parameter is carried in the second part of the first signaling.

[0278] Optionally, the first device receives configuration information from the core network network element through the first signaling, including: the first device receives the first configuration parameter from the core network network element through the first part of the first signaling at a first moment, and the first device receives the second configuration parameter from the core network network element through the second part of the first signaling at a second moment; wherein the first moment and the second moment are the same, or the first moment and the second moment are different.

[0279] Optionally, the method further includes: the first device obtaining the type of the generated model and / or the function of the generated model.

[0280] In one implementation, before executing step S1010, the first device obtains the type of the generation model and / or the function of the generation model. The type of the generation model and / or the function of the generation model may be dynamically configured to the first device by a core network element through signaling or messaging, or may be pre-configured, for example, by pre-storing corresponding code, a table, or other methods that can be used to indicate the type of the generation model and / or the function of the generation model in the first device. This application does not limit the implementation method thereof.

[0281] Optionally, the type of the generative model can be any of the following: GMM, VAE, GAN. For specific explanations, please refer to the relevant descriptions above.

[0282] Optionally, the function of the generation model may be to be used for terminal device positioning, or for image recognition, etc. For example, when positioning a terminal device, the function of the generation model may be to output a probability distribution of the terminal device's position coordinate information, or to output a probability distribution of measurement results of a measurement quantity used for terminal device positioning, etc.

[0283] Exemplarily, the first device can determine the GMM used for positioning the terminal device based on the type of the generation model and / or the function of the generation model. That is, the first device can determine that the generation model that needs to be trained or fitted is the GMM through the type of the generation model and / or the function of the generation model, and locate the terminal device through the trained or fitted GMM.

[0284] S1020: The first device processes the channel measurement result using the first model to obtain a probability distribution of the measurement result of the measurement quantity used for positioning the terminal device.

[0285] The first model is determined based on the configuration parameters of the generative model. This can be understood as follows: the first device can fit or train the first model based on the obtained configuration parameters of the generative model. If the generative model is a GMM, this means that the first device can train or fit a specific GMM or a specific class of GMMs based on the configuration parameters. In other words, the first model is a trained GMM model and can be used for terminal device positioning. For example, the first model is a GMM obtained by iterating 50 times using the EM algorithm. The trained GMM may include three single Gaussian models.

[0286] For example, the measurement quantity may include one or more of the following:

[0287] (1) RSTD;

[0288] For example, RSTD may also be referred to as TDoA. For specific interpretation and implementation, please refer to the relevant description of FIG. 7 above.

[0289] (2)TDoA;

[0290] For example, TDoA is a positioning method using time difference. For a specific implementation method, please refer to the relevant description of FIG. 7 above.

[0291] (3)ToA;

[0292] For example, ToA is a method for calculating the physical distance by using the transmission delay of a wireless signal between two nodes, that is, determining the location by measuring the time interval from sending a signal to receiving a signal, which usually requires synchronized timing at the receiving node.

[0293] (4)AoA;

[0294] For example, a low energy (LE) device can make its direction available to a peer device by sending a data packet with direction finding capabilities using a single antenna. The peer device includes a radio frequency switch and an antenna array that switches antennas and acquires in-phase and quadrature (IQ) signal samples when receiving partial data packets. The IQ signal samples can be used to calculate the phase difference of the radio signals received by different elements of the antenna array, which can then be used to estimate the angle of arrival (AoA).

[0295] (5)LoS probability;

[0296] Exemplarily, the LoS probability is used to determine the NLoS degree of the channel environment. Different NLoS degrees (i.e., different channel conditions) have different impacts on the inference accuracy of the generated model. Therefore, the first device can determine the NLOS degree of the channel based on the channel measurement results, thereby determining the current channel conditions. For example, LOS (1) or NLOS (0) can be used to indicate that the LOS between the network device and the terminal device is not blocked by an obstruction, and the reference signal transmitted between the network device and the terminal device is not affected.

[0297] It should be noted that LOS refers to signal transmission between the transmitting and receiving antennas at a distance where they can see each other. This means that there are no obstacles between the two antennas that could affect signal transmission, and the signal can be fully transmitted. Non-line-of-sight (NLoS) refers to signal transmission between the transmitting and receiving antennas at a distance where they cannot see each other. This means that there are obstacles between the two antennas that could affect signal transmission, and the signal cannot be fully transmitted.

[0298] It should be understood that the RSTD, TDoA, ToA, AoA, and LoS probability described above can be considered as measurement quantities for a channel measurement. A channel can include one or more pathnames (e.g., a set of pathnames). For example, the LoS probability can be the average LoS probability of the line-of-sight identification results corresponding to all pathnames in a channel. The ToA estimation result can be the average of the arrival times corresponding to all pathnames in a channel. The AoA estimation result can be the average of the arrival angles corresponding to all pathnames in a channel, etc.

[0299] It should be noted that the measurement quantity in the embodiment of the present application may be one or more of the above-mentioned parameters (1)-(5), and correspondingly, the channel measurement result may also be one or more, and the probability distribution of the measurement result of the measurement quantity used for terminal device positioning may also be one or more. This application does not limit this.

[0300] In a possible implementation of the embodiment of the present application, the channel measurement result is based on the measurement of the reference signal.

[0301] In the first example, the channel measurement result may be obtained by the first device measuring the reference signal.

[0302] For example, in an uplink positioning scenario, when the first device is a network device, the channel measurement result is obtained based on a first channel measurement, and the first channel measurement includes: the network device measures a sounding reference signal (eg, SRS) from the terminal device.

[0303] For another example, in a downlink positioning scenario, when the first device is a terminal device, the channel measurement result is obtained based on a second channel measurement, where the second channel measurement includes: the terminal device measuring a positioning reference signal (e.g., a PRS or a preamble) or a channel state information reference signal (CSI-RS) from an access network device;

[0304] For example, in a sidelink positioning scenario, when the first device is a first terminal device, the channel measurement result is obtained based on a third channel measurement, and the third channel measurement includes: the first terminal device measures a sidelink positioning reference signal (SL-PRS) from the second terminal device.

[0305] In the second example, the channel measurement result may also be obtained by measuring the reference signal by other devices (such as a network element that performs channel measurement, or a channel measurement network element, or other devices such as a reference signal measurement node), and this application does not limit this.

[0306] It should be noted that the embodiments of the present application are primarily illustrative of channel measurement based on a reference signal to obtain channel measurement results, and are not intended to be limiting. For example, the channel measurement results may also include pedestrian dead-reckoning (PDR) measurement results of a terminal; or the channel measurement results may also include environmental monitoring and recognition results from a camera, such as environmental monitoring and recognition results from a surveillance camera in an indoor factory.

[0307] In an embodiment of the present application, the measurement quantity corresponds to the channel measurement result, which can be understood as follows: the first device measures one or more measurement quantities corresponding to the reference signal to obtain a channel measurement result, and the measurement result is the measurement result of the one or more measurement quantities. For example, taking the downlink positioning scenario as an example, assuming that the measurement quantity is TDoA, the first device is a terminal device, network device #1 can send a reference signal to the terminal device, such as PRS#1, and network device #2 can send PRS#2 to the terminal device. Correspondingly, the terminal device can measure the TDoA of PRS#1 and PRS#2, such as t2-t1, which can be used as channel measurement result #1, where t1 represents the transmission time when network device #1 transmits signals to the terminal device, and t2 represents the transmission time when network device #2 transmits signals to the terminal device. Optionally, network device #1 and network device #2 can send PRS multiple times, or network device #3 can also send PRS #3 to the terminal device. Correspondingly, the terminal device can measure the TDoA of PRS #2 and PRS #3, for example, t3-t2, which can be used as channel measurement result #2, where t3 represents the transmission time when network device #3 transmits signals to the terminal device, and so on.

[0308] Below, an example is given of the first device processing the channel measurement result using the first model to obtain the probability distribution of the measurement result of the measurement quantity used for terminal device positioning.

[0309] In one example, the first device may use the channel measurement results (or channel features extracted from the channel measurement results, this application uses the channel measurement results as an example) as the input of the first model, and the output of the first model is used to directly or indirectly determine the position of the terminal device, such as the output of the first model may be a probability distribution of the measurement results of the measurement quantity used for positioning the terminal device.

[0310] For example, when the generation model is GMM, the first model can be a GMM fitted or trained according to the configuration parameters of GMM, and the first device can use the channel measurement result #1 and channel measurement result #2 obtained above as the input of GMM respectively, and the corresponding probability distribution of GMM of TDoA for terminal device positioning can be obtained.

[0311] For another example, when the generation model is VAE, the first model may be a VAE obtained by fitting or training according to the configuration parameters of the VAE. The first device may use the channel measurement result #1 and channel measurement result #2 obtained above as inputs of the VAE, respectively, and the corresponding variational probability distribution of TDoA for terminal device positioning may be obtained.

[0312] It should be noted that the embodiments of the present application do not specifically limit the input of the first model, that is, the number of channel measurement results corresponding to a certain measurement quantity. Alternatively, it can generally be understood that the greater the number of channel measurement results, the more accurate the probability distribution of the corresponding measurement quantity, and thus the higher the positioning accuracy of the terminal device.

[0313] For example, the estimated distance between two nodes (that is, the product of the transmission delay ToA between the two nodes and the propagation speed of electromagnetic waves) is taken as an example. The propagation speed of electromagnetic waves in free space is equal to the speed of light, which is c = 299792458 m / s ≈ 3×10 8 m / s. GMM (i.e., the first model) is used to describe the probability distribution of the distance estimate.

[0314] For example, the commonly used estimation algorithm is the maximum likelihood (ML) estimation, and a set of distance estimation value vector sequences for training can be set as X = {x1, x2, ..., x N}, which includes the distance estimation values ​​in LOS and NLOS environments, and N is an integer greater than 1. The probability density function of the distance estimation value under line-of-sight conditions satisfies: x=x1,x2,…,x N , where r LOS Indicates the real distance in the line-of-sight environment. When the indoor environment is stable, the value is set to 0. Represents the variance in the line-of-sight environment, that is, the distance estimate x obeys the Gaussian distribution. At this time, represents the mean of the Gaussian distribution, Represents the variance of the Gaussian distribution. The probability density function of the distance estimate x in a non-line-of-sight environment satisfies: in, That is, the distance estimate x obeys Gaussian distribution, then r NLOS represents the mean of the Gaussian distribution, Represents the variance of the Gaussian distribution. From this, we can get the probability density function of a K-order mixed Gaussian model, which is expressed as:

[0315] Where θ=(r k ,σ k ,p k ), x=x1,x2,…,x N , represents the N-dimensional joint Gaussian probability distribution of the k-th single Gaussian model, σ k is the variance or covariance matrix of the kth single Gaussian model, r kis the expected value of the k-th single Gaussian model, representing the estimated distance between two nodes, p k is the weight of the k-th single Gaussian model in the Gaussian mixture model,

[0316] It should be understood that both the probability distribution function and the probability density function are functions that describe the probability of a random variable within a certain interval. Assuming that F(x) is the probability distribution function of the random variable X and f(x) is the probability density function of X, then F(x) = ∫f(x)dx. Among them, the probability distribution function represents the probability of the random variable taking values within a certain interval, and the probability density function represents the probability density of the random variable taking values at a certain point.

[0317] For example, by using the EM algorithm to iterate the estimated values of the weight, expectation, variance or covariance of the k-th single Gaussian model in the GMM, the following can be obtained:

[0318] The iterative formula for the estimated value of the weight is:

[0319] The iterative formula for the estimated value of the expected value is:

[0320] The iterative formula for the estimated value of the variance or covariance is:

[0321] Among them, p(k|n) in the above three formulas is the posterior probability, which can be expressed as:

[0322] It should be understood that the EM algorithm can better solve the problem of estimating the parameters of the Gaussian mixture model of training samples using the maximum likelihood algorithm. After collecting a large number of distance measurement values, the distance estimated value is obtained through the EM algorithm to achieve the positioning estimation of the terminal device.

[0323] Optionally, after performing the above step S1020, the method 1000 further includes step S1030.

[0324] S1030, the first device sends the first information to the core network element. Correspondingly, the core network element receives the first information from the first device.

[0325] Among them, the first information is used to indicate the probability distribution of the measurement results of the measurement quantities for terminal device positioning.

[0326] In the first example, when the generative model is GMM, the first information can indicate the GMM of the measurement quantities for terminal device positioning. For example, assuming that the GMM includes k single Gaussian models, where k is an integer greater than or equal to 1, at this time the first information can include one or more of the following:

[0327] (1) k expected values The value of

[0328] (2) k variances or covariances The value of

[0329] (3) The proportion of k single Gaussian models in the Gaussian mixture model The value of

[0330] Among them, the k expected values, k variances or covariances correspond one-to-one to the k single Gaussian models. For specific interpretations, please refer to the relevant description of the above formula (3).

[0331] It should be understood that the above parameters (1)-(3) can be specific values, where and are all positive numbers. The core network element can determine the first model fitted or trained by the first device based on the parameters (1)-(3) included in the first information, that is, the GMM, and then the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the first model can be more accurate, thereby improving the positioning accuracy of the terminal device.

[0332] In the second example, when the generative model is a VAE, the first information may indicate a variational probability distribution of a measurement quantity used for terminal device positioning. In this case, the first information may include one or more of the following:

[0333] (1) The values ​​of VAE model parameters;

[0334] For example, the values ​​of the VAE model parameters may include one or more of the following: the weight of the neuron w = [w, w1, ..., w n ], or, the bias in the activation function of the neuron (or the bias of the neural network) b.

[0335] (2) The value of the probability distribution output by VAE.

[0336] Exemplarily, the value of the probability distribution output by VAE may be the value of the probability distribution of the measurement result for a certain measurement quantity. For example, when the measurement quantity is TDoA, the value of the probability distribution output by VAE may include the probability distribution values ​​x, y, and z corresponding to t2-t1, t3-t2, and t3-t1, wherein t2-t1 may represent the channel measurement result #1 obtained by the terminal device measuring the TDoA of PRS#1 and PRS#2, t3-t2 represents the channel measurement result #2 obtained by the terminal device measuring the TDoA of PRS#3 and PRS#2, and t3-t1 represents the channel measurement result #3 obtained by the terminal device measuring the TDoA of PRS#3 and PRS#1. PRS#1, PRS#2, and PRS#3 may be the reference signals sent to the terminal device by network device #1, network device #2, and network device #3, respectively.

[0337] It should be understood that the above parameters (1)-(2) can be specific values, where w, w1, ..., w n , b, x, y, and z are all positive numbers. The core network element can determine the first model fitted or trained by the first device, that is, VAE, based on the parameters (1)-(2) included in the first information. Then, the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the first model can be more accurate, thereby improving the positioning accuracy of the terminal device.

[0338] Optionally, after executing the above step S1030, the method 1000 further includes step S1040.

[0339] S1040: The core network element determines the location of the terminal device according to the probability distribution of the measurement results of the measurement quantity and the configuration parameters of the generation model.

[0340] In the first example, assuming that the generation model is GMM, the core network element can determine the location of the terminal device according to the GMM distribution of the measurement quantity and the configuration information of the generation model.

[0341] For example, taking the uplink positioning scenario as an example, P first devices (e.g., network devices) may respectively send P GMM probability distributions of measurement quantities for terminal device positioning to the core network element. Optionally, for the same measurement quantity (e.g., TDoA), the number of single Gaussian models contained in the first model (i.e., GMM) corresponding to each GMM probability distribution in the P GMM probability distributions may be different, and the expected value, variance or covariance value, and proportion of each single Gaussian model in the entire GMM may be different.

[0342] For example, assuming that the number of single Gaussian models contained in the GMM corresponding to each GMM distribution is the same k=3, and the first information reported by each network device contains the expected values ​​and variance values ​​of 3 single Gaussian models, then the core network network element can average the expected values ​​and variance values ​​of the 3 single Gaussian models in P first information, and then obtain the expected average value and the average value of the variance of these 3 single Gaussian models, and then obtain a more accurate TDoA estimate based on the average value of the expected average value and the variance. Alternatively, the core network network element can also calculate the first information reported by each network device separately to obtain the corresponding TDoA estimate, and then take the average value of all TDoA estimates to obtain the final TDoA estimate, and perform more accurate positioning of the terminal device based on the TDoA estimate. This application does not limit this.

[0343] For another example, assuming P=2, the number of single Gaussian models corresponding to the GMM probability distribution sent by network device #1 to the core network network element is 3, and the first information reported by network device #1 includes the expected values ​​and variance values ​​of these 3 single Gaussian models, the number of single Gaussian models corresponding to the GMM probability distribution sent by network device #2 to the core network network element is 2, and the first information reported by network device #2 includes the expected values ​​and variance values ​​of these 2 single Gaussian models, then the core network network element can obtain an estimated value of TDoA#1 based on the expected values ​​and variance values ​​of the 3 single Gaussian models reported by network device #1, and obtain TDoA#2 based on the expected values ​​and variance values ​​of the 2 single Gaussian models reported by network device #2, and then average TDoA#1 and TDoA#2 to obtain the final estimated value of TDoA, and perform more accurate positioning of the terminal device based on the estimated value of TDoA.

[0344] For another example, assuming P=2, the number of single Gaussian models corresponding to the GMM probability distribution sent by network device #1 to the core network element is 3, and the first information reported by network device #1 includes the expected values ​​and proportions (or weights) of the three single Gaussian models; the number of single Gaussian models corresponding to the GMM probability distribution sent by network device #2 to the core network element is 3, and the first information reported by network device #2 includes the expected values ​​and proportions (or weights) of the three single Gaussian models. The core network element can average the product of the expected values ​​and proportions (or weights) of the three single Gaussian models in the two first information, and then obtain the weighted average of the expected values ​​of the three single Gaussian models corresponding to the GMM probability distribution, and then obtain a more accurate TDoA estimate based on the weighted average. This application does not limit this.

[0345] In the second example, assuming that the generative model is VAE, the core network element can determine the location of the terminal device based on the variational probability distribution of the measured quantity and the configuration information of the generative model.

[0346] For example, taking the uplink positioning scenario as an example, Q first devices (such as network devices) can respectively send the variational probability distribution of the measurement quantity used for terminal device positioning to the core network network element. Optionally, for the same measurement quantity (such as TDoA), the values ​​of the probability distribution corresponding to the Q variational probability distributions may be different. For example, the values ​​x, y, and z of the probability distribution corresponding to the measurement results t2-t1, t3-t2, and t3-t1 in each variational probability distribution may be different. Optionally, the core network network element can select a higher probability distribution value from the Q variational probability distributions, and then obtain a more accurate TDoA estimate based on the higher probability distribution value, and more accurately locate the terminal device based on the TDoA estimate.

[0347] In the embodiments of the present application, the transmission of information / or data between devices is not limited to direct transmission, indirect transmission (including transparent transmission), etc. Therefore, device A sends information to device B, which includes device A sending the information directly to device B through the interface between device A and device B, and may also include device A sending the message to device C, and device C sending the message to device B. There is also no limit on the number of relay forwardings from device A to device B. For example, the UE sends the first information to the LMF, which may include: the UE sends the first information directly to the LMF through an LPP message; or the UE sends the first information to the LMF through the gNB; or the UE sends the first information to the LMF through the gNB and AMF, and the UE sends the first information to the LMF through the AMF, etc. Various specific implementations are not limited. The interactions between other devices are similar, which can be understood by those skilled in the art and will not be repeated here. For the interface messages between the devices, please refer to the description in Figure 4.

[0348] According to the above scheme, the core network network element sends configuration information to the first device, so that the core network network element and the first device can align the configuration information of the generated model, and can obtain that the first model fitted / trained for terminal device positioning is the same. Therefore, the core network network element can analyze and apply the probability distribution of the measurement results of the measurement quantity based on the first model more accurately, and can further improve the positioning accuracy of the terminal device.

[0349] It should be understood that in the solution shown in FIG10 above, the core network element sends configuration information to the first device, so that the first device determines the first model for fitting / training the terminal device positioning, and then obtains the probability distribution of the measurement result of the measurement quantity based on the first model. It should be noted that the present application is also applicable to the terminal device reporting configuration information to the core network element to notify the first model for fitting / training the terminal device positioning, so that the core network element can more accurately analyze and apply the probability distribution of the measurement result of the measurement quantity based on the first model. For specific implementation methods, please refer to the relevant description of FIG11 below.

[0350] Figure 11 is a schematic flow chart of a communication method 1100 provided in an embodiment of the present application. As shown in Figure 11, the following multiple steps are included. It should be understood that the method can be executed by the first device and the core network element, or it can also be executed by the chip or circuit of the first device and the core network element, and this application does not limit this. For the convenience of description, the following example is illustrated with the first device and the core network element as the execution subject. For the convenience of description, the following example is illustrated with the first device and the core network element as the execution subject. It should be noted that the model training / fitting in this implementation method occurs on the first device side, and the model reasoning / use occurs on the core network element side, or the model training / fitting occurs on the OTT or third-party device or cloud device side, and the model reasoning / use occurs on the OTT or third-party device or cloud device side, and this application does not limit this.

[0351] S1110: The first device obtains configuration information, where the configuration information is used to indicate configuration parameters of a generated model.

[0352] Exemplarily, the configuration information is used to indicate configuration parameters of the generation model. For details of the configuration information, the generation model, and the configuration parameters, please refer to the description of step S1010 of the above method 1000.

[0353] In one example, the first device may be a terminal device or an access network device, and the core network element may be a positioning device, such as a location management function network element (such as an LMF). The first device may also be referred to as a network element that performs channel measurement, or a channel measurement network element, or a reference signal measurement node, etc., and this application does not limit these names.

[0354] Optionally, the configuration information may be dynamically configured through signaling or messages, or may be autonomously determined by the first device, or may be pre-configured. For example, the configuration information may be implemented by pre-saving corresponding codes, tables, or other methods that can be used to indicate the configuration information in the first device. This application does not limit this.

[0355] Optionally, the configuration parameters include a first configuration parameter and a second configuration parameter. For example, the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or the configuration information is used to indicate a portion of the configuration parameters (e.g., the first configuration parameter or the second configuration parameter), and the other configuration parameters can be determined based on a mapping relationship. For specific implementation methods, please refer to the relevant description of method 900 above.

[0356] Optionally, the method further includes: the first device obtaining the type of the generated model and / or the function of the generated model.

[0357] In one implementation, before executing step S1110, the first device obtains the type of the generation model and / or the function of the generation model. The type of the generation model and / or the function of the generation model may be dynamically configured to the first device through signaling or messages, or may be pre-configured, for example, by pre-storing corresponding codes, tables, or other methods that can be used to indicate the type of the generation model and / or the function of the generation model in the first device, which is not limited in this application.

[0358] The type of the generated model and / or the content of the function of the generated model may refer to the relevant description of the above-mentioned method 1000.

[0359] S1120: The first device processes the channel measurement result using the first model to obtain a probability distribution of the measurement result of the measurement quantity used for positioning the terminal device.

[0360] The first model is determined based on the configuration parameters of the generated model, the measurement quantity corresponds to the channel measurement result, and the channel measurement result is based on the measurement of the reference signal. For specific interpretations, please refer to the relevant description of step S1020 of the above method 1000.

[0361] Exemplarily, the measurement quantity may include one or more of the following: RSTD, TDoA, ToA, AoA, LoS probability, LoS and NLoS identification results. For the specific interpretation of the measurement quantity and the specific implementation method of this step, please refer to the relevant description of step S1020 of the above method 1000.

[0362] Optionally, after executing the above step S1120, the method 1100 further includes step S1130.

[0363] S1130, the first device sends all or part of the first information and configuration information to the core network network element, and correspondingly, the core network network element receives all or part of the first information and configuration information from the first device.

[0364] Optionally, all or part of the first information and the configuration information may be sent via one signaling (or one data packet), or may be sent separately via two signalings (or two data packets), and this application does not limit this. Optionally, all or part of the first information and the configuration information may be sent simultaneously, or may be sent separately. For example, the first device may first send the first information and then send the configuration information; or, the first device may first send the configuration information and then send the first information. In other words, this application does not limit the timing of sending all or part of the first information and the configuration information.

[0365] Exemplarily, the first information is used to indicate the probability distribution of the measurement result of the measurement quantity used for positioning the terminal device. For the specific interpretation of the first information, please refer to the relevant description of step S1030 of the above method 1000.

[0366] It should be understood that the configuration information in step S1130 may be the configuration information obtained in the above step S1110. The configuration information may indicate all configuration parameters of the generated model or some configuration parameters of the generated model. For the specific implementation method, please refer to the relevant description of the above method 1000.

[0367] Optionally, the configuration information in step S1130 may also be partial configuration information obtained in the above step S1110. For example, the configuration information obtained in step S1110 indicates all configuration parameters of the generation model. The first device may send the first configuration parameter or the second configuration parameter to the core network element according to the mapping relationship in Table 1 to save signaling overhead. Correspondingly, the core network element may determine all configuration parameters of the generation model according to the mapping relationship in Table 1 or parameters predefined in other protocols.

[0368] Optionally, the configuration information in step S1130 may also be the full set of configuration information obtained in step S1110. For example, the configuration information obtained in step S1110 indicates the first configuration parameter of the generation model, and the first device may also send the corresponding second configuration parameter to the core network element according to the mapping relationship in Table 1. This application does not specifically limit this. Optionally, after executing step S1130, the method 1100 further includes step S1140.

[0369] S1140 , the core network element determines the location of the terminal device according to the probability distribution of the measurement results of the measurement quantity and the configuration parameters of the generation model.

[0370] Exemplarily, assuming that the generation model is GMM, the core network element can determine the location of the terminal device based on the GMM distribution of the measurement quantity and the configuration information of the generation model.

[0371] For example, taking the uplink positioning scenario as an example, multiple first devices (such as network devices) can respectively send GMM distributions of measurement quantities for terminal device positioning to the core network element. Optionally, for the same measurement quantity (such as TDoA), the number of single Gaussian models contained in the first model (i.e., GMM) corresponding to each GMM distribution may be different, and the number of iterations of the first model (i.e., GMM) may be different. Optionally, the core network element may select a GMM distribution with higher convergence accuracy, such as a GMM distribution with a larger number of single Gaussian models and a larger number of iterations of the first model, thereby obtaining a more accurate estimate of TDoA, and performing more accurate positioning of the terminal device based on the estimated value of TDoA.

[0372] Exemplarily, assuming that the generation model is VAE, the core network element can determine the location of the terminal device based on the variational probability distribution of the measurement quantity and the configuration information of the generation model. The specific implementation method can refer to the relevant description of step S1040 of the above method 1000.

[0373] For example, taking the uplink positioning scenario as an example, multiple first devices (such as network devices) can respectively send the variational probability distribution of the measurement quantity used for terminal device positioning to the core network network element. Optionally, for the same measurement quantity (such as TDoA), the value of each variational probability distribution may be different. For example, the values ​​x, y, and z of the probability distribution corresponding to the measurement results t2-t1, t3-t2, and t3-t1 in each variational probability distribution may be different. Optionally, the core network network element may select a variational probability distribution with a higher value of the probability distribution, thereby obtaining a more accurate estimate of the TDoA, and performing more accurate positioning of the terminal device based on the estimated value of the TDoA.

[0374] According to the above scheme, the first device sends configuration information to the core network network element, so that the configuration information of the generated model can be aligned between the core network network element and the first device, and it can be learned that the first model fitted / trained for terminal device positioning is the same, and then the analysis and application of the probability distribution of the measurement results of the measurement quantity based on the first model can be more accurate, which can further improve the positioning accuracy of the terminal device.

[0375] The following, in conjunction with Figures 12 to 17, illustrates the application of the embodiments of the present application in the uplink positioning scenario, downlink positioning scenario, and side positioning scenario, respectively. It should be understood that the method embodiments shown in Figures 10 to 17 can be combined with each other, and the steps in the method embodiments shown in Figures 10 to 17 can be referenced to each other. For example, in the embodiments of the present application, the method embodiments shown in Figures 12 to 17 can be regarded as possible implementation methods for realizing the functions of the method embodiments shown in Figures 10 and 11, wherein Figures 12 and 15 are mainly used to illustrate the uplink positioning scenario, Figures 13 and 16 are mainly used to illustrate the downlink positioning scenario, and Figures 14 and 17 are mainly used to illustrate the side positioning scenario.

[0376] Figure 12 is a flow chart illustrating a communication method 1200 according to an embodiment of the present application. As shown in Figure 12, taking the LMF as a core network element, the first device as a gNB, and the second device as a UE as an example, model training / fitting in this implementation occurs on the gNB side, while model inference / use occurs on the LMF side. It should be understood that the descriptions of the embodiments shown in Figures 10 and 11 above also apply to this implementation, and that the same or similar technical means may exist between Figures 10 and 12. The details already described in Figure 12 and the embodiments shown in Figures 10 and 11 will not be repeated here.

[0377] It should be understood that this implementation uses the GMM generation model as an example. The gNB measures the SRS to obtain measurement results of the measurement quantity. Furthermore, the gNB determines GMM1 based on configuration information #1 sent by the LMF and processes the channel measurement results using GMM1 to obtain a GMM distribution (corresponding to method one). Alternatively, the gNB reports configuration information #1 and GMM1 parameters to the LMF (corresponding to method two), so that the gNB and LMF align configuration information #1, ensuring that the fitted / trained GMM1 used for UE positioning is the same. This ensures that the analysis and application of the probability distribution of the measurement results of the measurement quantity based on GMM1 is more accurate, thereby improving UE positioning accuracy.

[0378] Method 1:

[0379] S1210: The LMF sends configuration information #1 to the gNB. Correspondingly, the gNB receives configuration information #1 from the LMF.

[0380] The content, interpretation, and specific implementation of configuration information #1 may refer to the description of step S1010 of the above method 1000 .

[0381] S1220: The UE sends an SRS to the gNB. Correspondingly, the gNB receives the SRS from the UE.

[0382] S1230. The gNB determines the measurement quantity GMM1 for UE positioning based on the channel measurement result #1 and the configuration information #1.

[0383] Exemplarily, the gNB measures the SRS to obtain channel measurement result #1. Based on the configuration information #1, GMM1 can be determined, and the channel measurement result #1 is used as the input of GMM1. The output of GMM1 is GMM1.

[0384] The content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #1, and the specific implementation of this step may refer to the relevant description of step S1020 of the above method 1000.

[0385] S1240: The gNB sends the GMM1 parameters to the LMF. Correspondingly, the LMF receives the GMM1 parameters from the gNB.

[0386] The contents and definitions of the parameters of GMM1, as well as the specific implementation of this step, may refer to the relevant description of step S1030 of the above method 1000.

[0387] S1250, LMF determines the location of the UE based on configuration information #1 and parameters of GMM1.

[0388] For the specific implementation, please refer to the relevant description of step S1040 of the above method 1000.

[0389] Method 2:

[0390] S1260: The UE sends an SRS to the gNB. Correspondingly, the gNB receives the SRS from the UE.

[0391] S1270. The gNB determines the measurement quantity GMM1 for UE positioning based on the channel measurement result #1.

[0392] Exemplarily, the gNB measures the SRS to obtain channel measurement result #1, and uses the channel measurement result #1 as the input of GMM1, and the output of GMM1 is GMM1.

[0393] The content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #1, and the specific implementation method can refer to the relevant description of step S1120 of the above method 1100.

[0394] S1280: The gNB sends the parameters and configuration information #1 of GMM1 to the LMF. Correspondingly, the LMF receives the parameters and configuration information #1 of GMM1 from the gNB.

[0395] The parameters of GMM1 and the content of configuration information #1, their interpretations, and specific implementation methods may refer to the relevant description of step S1130 of the above method 1100.

[0396] S1290, LMF determines the location of the UE based on the parameters of GMM1 and configuration information #1.

[0397] For the specific implementation method, please refer to the relevant description of step S1140 of the above method 1100.

[0398] In this embodiment of the present application, using the GMM generation model as an example, the gNB measures the SRS measurement quantity to obtain measurement results. Furthermore, the gNB and LMF align the configuration parameters of GMM1 by sending configuration information #1, ensuring that the GMM1 used for fitting / training UE positioning is the same. This ensures more accurate analysis and application of the probability distribution of the measurement results based on GMM1, thereby improving UE positioning accuracy.

[0399] Figure 13 is a flow chart of a communication method 1300 provided in an embodiment of the present application. As shown in Figure 13 , taking the LMF as a core network element, the first device as a UE, and the second device as a gNB as an example, model training / fitting in this implementation occurs on the UE side, while model inference / use occurs on the LMF side. It should be understood that the relevant descriptions of the embodiments shown in Figures 10 and 11 above also apply to this implementation, and that the same or similar technical means may exist between Figures 10, 11, and 13. The details already described in Figure 13 and the embodiments shown in Figures 10 and 11 will not be repeated here.

[0400] It should be understood that this implementation method takes the generation model as GMM as an example, and the UE obtains the measurement result of the measurement quantity by measuring the PRS. Furthermore, the UE determines GMM2 based on the configuration information #2 sent by the LMF, and uses GMM2 to process the channel measurement result to obtain the GMM distribution (corresponding to method one). Alternatively, the UE reports the configuration information #2 and the parameters of GMM2 to the LMF (corresponding to method two), so that the UE and the LMF align the configuration information #2, ensuring that the GMM2 fitted / trained for UE positioning is the same, thereby ensuring that the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the GMM2 is more accurate, thereby improving the positioning accuracy of the UE.

[0401] Method 1:

[0402] S1310, LMF sends configuration information #2 to UE, and correspondingly, UE receives configuration information #2 from LMF.

[0403] The content, interpretation, and specific implementation of configuration information #2 may refer to the description of step S1010 of the above method 1000 .

[0404] S1320: The gNB sends a PRS to the UE. Correspondingly, the UE receives the PRS from the gNB.

[0405] S1330 : The UE determines GMM2 of the measurement amount used for UE positioning according to the channel measurement result #2 and the configuration information #2.

[0406] Exemplarily, the UE measures the PRS to obtain a channel measurement result #2, and can determine GMM2 according to the configuration information #2. The channel measurement result #2 is used as the input of GMM2, and the output of GMM2 is GMM1.

[0407] The content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #2, and the specific implementation method can refer to the relevant description of step S1020 of the above method 1000.

[0408] S1340, the UE sends GMM2 parameters to the LMF, and correspondingly, the LMF receives the GMM2 parameters from the UE.

[0409] The contents and definitions of the parameters of GMM2, as well as the specific implementation methods, can be found in the relevant description of step S1030 of the above method 1000.

[0410] S1350, LMF determines the location of the UE based on the parameters of GMM2 and configuration information #2.

[0411] For the specific implementation, please refer to the relevant description of step S1040 of the above method 1000.

[0412] Method 2:

[0413] S1360: The gNB sends a PRS to the UE. Correspondingly, the UE receives the PRS from the gNB.

[0414] S1370 , the UE determines GMM2 of the measurement amount used for UE positioning according to the channel measurement result # 2 .

[0415] Exemplarily, the UE measures the PRS to obtain a channel measurement result #2, and uses the channel measurement result #2 as an input of GMM2. The output of GMM2 is GMM1.

[0416] For the content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #2, and the specific implementation method, please refer to the relevant description of step S1120 of the above method 1100.

[0417] S1380, the UE sends GMM2 parameters and configuration information #2 to the LMF, and correspondingly, the LMF receives GMM2 parameters and configuration information #2 from the UE.

[0418] The parameters of GMM2 and the content and interpretation of configuration information #2, as well as the specific implementation method, can be found in the relevant description of step S1130 of the above method 1100.

[0419] S1390, LMF determines the location of the UE based on the parameters of GMM2 and configuration information #2.

[0420] For the specific implementation method, please refer to the relevant description of step S1140 of the above method 1100.

[0421] In this embodiment of the present application, using the GMM generation model as an example, the UE measures the PRS measurement quantity to obtain a measurement result of the measurement quantity. Furthermore, the UE and LMF align the configuration parameters of GMM2 by sending configuration information #2, so that the GMM2 fitted / trained for UE positioning is the same. This ensures more accurate analysis and application of the probability distribution of the measurement result of the measurement quantity based on the GMM2, thereby improving the UE's positioning accuracy.

[0422] Figure 14 is a flow chart of a communication method 1400 provided in an embodiment of the present application. As shown in Figure 14, taking LMF as a core network element, UE#1 as the first device, and UE#2 as the second device as an example, the model training / fitting in this implementation occurs on the UE#1 side, and the model reasoning / use occurs on the LMF side. It should be understood that the relevant descriptions in the embodiments shown in Figures 10 and 11 above are also applicable to this implementation, and the same or similar technical means may exist between Figures 10, 11, and 14. The contents described in the embodiments shown in Figures 14 and 10 and 11 will not be repeated here.

[0423] It should be understood that this implementation method takes the generation model as GMM as an example, and UE1 obtains the measurement result of the measurement quantity by measuring the SL-PRS. Furthermore, UE1 determines GMM3 based on the configuration information #3 sent by the LMF, and uses GMM3 to process the channel measurement result to obtain the GMM distribution (corresponding to method one). Alternatively, UE1 reports the configuration information #3 and the parameters of GMM3 to the LMF (corresponding to method two), so that UE1 and LMF align the configuration information #3, ensure that the GMM3 fitted / trained for UE positioning is the same, and further ensure that the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the GMM3 is more accurate, thereby improving the positioning accuracy of the UE.

[0424] Method 1:

[0425] S1410, LMF sends configuration information #3 to UE#1, and correspondingly, UE#1 receives configuration information #3 from LMF.

[0426] The content, meaning, and specific implementation of configuration information #3 may refer to the description of step S1010 of the above method 1000 .

[0427] S1420, UE#2 sends SL-PRS to UE#1, and correspondingly, UE#1 receives SL-PRS from UE#2.

[0428] S1430 , UE# 1 determines GMM3 of the measurement amount used for UE positioning according to channel measurement result # 3 and configuration information # 3.

[0429] Exemplarily, UE#1 measures SL-PRS to obtain channel measurement result #3, and GMM3 can be determined based on the configuration information #3. The channel measurement result #3 is used as the input of GMM3, and the output of GMM3 is GMM1.

[0430] For the content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #3, and the specific implementation method, please refer to the relevant description of step S1020 of the above method 1000.

[0431] S1440, UE#1 sends GMM3 parameters to LMF, and correspondingly, LMF receives GMM3 parameters from UE#1.

[0432] The contents and definitions of the parameters of GMM3, as well as the specific implementation methods, may refer to the relevant description of step S1030 of the above method 1000.

[0433] S1450, LMF determines the location of the UE based on the GMM3 parameters and configuration information #3.

[0434] For the specific implementation, please refer to the relevant description of step S1040 of the above method 1000.

[0435] Method 2:

[0436] S1460, UE#2 sends SL-PRS to UE#1, and correspondingly, UE#1 receives SL-PRS from UE#2.

[0437] S1470 , UE# 1 determines GMM3 of the measurement amount used for UE positioning according to channel measurement result # 3 .

[0438] Exemplarily, UE#1 measures the SL-PRS to obtain a channel measurement result #3, and uses the channel measurement result #3 as an input of GMM3, and the output of GMM3 is GMM1.

[0439] The content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #3, and the specific implementation method can be referred to the relevant description of step S1120 of the above method 1100.

[0440] S1480, UE#1 sends GMM3 parameters and configuration information #3 to LMF, and correspondingly, LMF receives GMM3 parameters and configuration information #3 from UE#1.

[0441] The parameters of GMM3 and the content and interpretation of configuration information #3, as well as the specific implementation method, can refer to the relevant description of step S1130 of the above method 1100.

[0442] S1490, LMF determines the location of the UE based on the GMM3 parameters and configuration information #3.

[0443] For the specific implementation method, please refer to the relevant description of step S1140 of the above method 1100.

[0444] In this embodiment of the present application, using the GMM generation model as an example, UE#1 measures the SL-PRS measurement quantity to obtain a measurement result of the measurement quantity. Furthermore, UE#1 and the LMF align the configuration parameters of GMM3 by sending configuration information #3, ensuring that the GMM3 fitted / trained for UE positioning is the same. This ensures more accurate analysis and application of the probability distribution of the measurement result of the measurement quantity based on the GMM3, thereby improving the UE's positioning accuracy.

[0445] Figure 15 is a flow chart of a communication method 1500 provided in an embodiment of the present application. As shown in Figure 15 , taking the LMF as a core network element, the first device as a gNB, and the second device as a UE as an example, model training / fitting in this implementation occurs on the gNB side, while model inference / use occurs on the LMF side. It should be understood that the relevant descriptions of the embodiments shown in Figures 10 and 11 above also apply to this implementation, and that the same or similar technical means may exist between Figures 10, 11, and 15. The details already described in Figure 15 and the embodiments shown in Figures 10 and 11 will not be repeated here.

[0446] It should be understood that this implementation uses the VAE as an example of a generation model. The gNB measures the SRS to obtain measurement results of the measurement quantity. Furthermore, the gNB determines VAE1 based on configuration information #4 sent by the LMF, and uses VAE1 to process the channel measurement results to obtain a variational probability distribution (corresponding to method one). Alternatively, the gNB reports configuration information #1 and the parameters of the variational probability distribution to the LMF (corresponding to method two), so that the gNB and LMF align configuration information #1, ensuring that the fitted / trained VAE1 used for UE positioning is the same. This ensures that the analysis and application of the probability distribution of the measurement results of the measurement quantity based on VAE1 is more accurate, thereby improving the UE's positioning accuracy.

[0447] Method 1:

[0448] S1510: The LMF sends configuration information #4 to the gNB. Correspondingly, the gNB receives configuration information #4 from the LMF.

[0449] The content, meaning, and specific implementation of configuration information #4 may be found in the description of step S1010 of the above method 1000 .

[0450] S1520: The UE sends an SRS to the gNB. Correspondingly, the gNB receives the SRS from the UE.

[0451] S1530: The gNB determines variational probability distribution #1 of the measurement quantity used for UE positioning based on channel measurement result #4 and configuration information #4.

[0452] For example, the gNB measures the SRS to obtain channel measurement result #4. Based on the configuration information #4, VAE1 can be determined, and the channel measurement result #4 is used as the input of VAE1. The output of VAE1 is variational probability distribution #1.

[0453] The content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #4, and the specific implementation method can refer to the relevant description of step S1020 of the above method 1000.

[0454] At step S1540, the gNB sends the parameters of variational probability distribution #1 to the LMF. Correspondingly, the LMF receives the parameters of variational probability distribution #1 from the gNB.

[0455] The contents and definitions of the parameters of variational probability distribution #1, as well as the specific implementation methods, can be found in the description of step S1030 of the above method 1000.

[0456] S1550, LMF determines the location of the UE based on configuration information #4 and parameters of variational probability distribution #1.

[0457] For the specific implementation, please refer to the relevant description of step S1040 of the above method 1000.

[0458] Method 2:

[0459] S1560: The UE sends an SRS to the gNB. Correspondingly, the gNB receives the SRS from the UE.

[0460] S1570: The gNB determines variational probability distribution #1 of the measurement quantity used for UE positioning based on channel measurement result #4.

[0461] For example, the gNB measures the SRS to obtain channel measurement result #4, and uses the channel measurement result #4 as the input of VAE1. The output of VAE1 is variational probability distribution #1.

[0462] For the content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #4, and the specific implementation method, please refer to the relevant description of step S1120 of the above method 1100.

[0463] At S1580, the gNB sends the parameters of variational probability distribution #1 and configuration information #4 to the LMF. Correspondingly, the LMF receives the parameters of variational probability distribution #1 and configuration information #4 from the gNB.

[0464] Among them, the parameters of variational probability distribution #1 and the content and interpretation of configuration information #4, as well as the specific implementation method can refer to the relevant description of step S1130 of the above method 1100.

[0465] S1590, LMF determines the location of the UE based on the parameters of variational probability distribution #1 and configuration information #4.

[0466] For the specific implementation method, please refer to the relevant description of step S1140 of the above method 1100.

[0467] In this embodiment of the present application, using the VAE generation model as an example, the gNB measures the SRS measurement quantity to obtain measurement results. Furthermore, the gNB and LMF align the configuration parameters of VAE1 by sending configuration information #4, ensuring that the fitted / trained VAE1 used for UE positioning is the same. This ensures more accurate analysis and application of the probability distribution of the measurement results based on VAE1, thereby improving UE positioning accuracy.

[0468] Figure 16 is a flow chart illustrating a communication method 1600 according to an embodiment of the present application. As shown in Figure 16 , taking the LMF as a core network element, the first device as a UE, and the second device as a gNB as an example, model training / fitting in this implementation occurs on the UE side, while model inference / use occurs on the LMF side. It should be understood that the descriptions of the embodiments shown in Figures 10 and 11 above also apply to this implementation, and that the same or similar technical means may exist between Figures 10, 11, and 16. The details already described in Figure 16 and the embodiments shown in Figures 10 and 11 will not be repeated here.

[0469] It should be understood that this implementation method takes the generation model as VAE as an example, and the UE obtains the measurement result of the measurement quantity by measuring the PRS. Furthermore, the UE determines VAE2 based on the configuration information #5 sent by the LMF, and uses VAE2 to process the channel measurement result to obtain the variational probability distribution (corresponding to method one), or the UE reports the configuration information #5 and the parameters of the variational probability distribution to the LMF (corresponding to method two), so that the UE and the LMF align the configuration information #5, ensuring that the VAE2 used for fitting / training of the UE positioning is the same, thereby ensuring that the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the VAE2 is more accurate, thereby improving the positioning accuracy of the UE.

[0470] Method 1:

[0471] S1610, LMF sends configuration information #5 to UE, and correspondingly, UE receives configuration information #5 from LMF.

[0472] The content, meaning, and specific implementation of configuration information #5 may refer to the description of step S1010 of the above method 1000 .

[0473] S1620: The gNB sends a PRS to the UE. Correspondingly, the UE receives the PRS from the gNB.

[0474] S1630: The UE determines a variational probability distribution #2 of a measurement variable used for UE positioning according to the channel measurement result #5 and the configuration information #5.

[0475] Exemplarily, the UE measures the PRS to obtain measurement result #5. VAE2 can be determined based on the configuration information #5, and the channel measurement result #5 is used as the input of VAE2. The output of VAE2 is variational probability distribution #2.

[0476] The content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #5, and the specific implementation method can refer to the relevant description of step S1020 of the above method 1000.

[0477] S1640, the UE sends the parameters of variational probability distribution #2 to the LMF, and the LMF receives the parameters of variational probability distribution #2 from the UE.

[0478] The contents and definitions of the parameters of variational probability distribution #2, as well as the specific implementation methods, can be found in the description of step S1030 of the above method 1000.

[0479] S1650, LMF determines the location of the UE based on configuration information #5 and parameters of variational probability distribution #2.

[0480] For the specific implementation, please refer to the relevant description of step S1040 of the above method 1000.

[0481] Method 2:

[0482] S1660: The gNB sends a PRS to the UE. Correspondingly, the UE receives the PRS from the gNB.

[0483] S1670: The UE determines a variational probability distribution #2 of a measurement variable used for UE positioning according to the channel measurement result #5.

[0484] Exemplarily, the UE measures the PRS to obtain measurement result #5, and uses the channel measurement result #5 as the input of VAE2. The output of VAE2 is variational probability distribution #2.

[0485] For the content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #5, and the specific implementation method, please refer to the relevant description of step S1120 of the above method 1100.

[0486] S1680, the UE sends the parameters of variational probability distribution #2 and configuration information #5 to the LMF. Correspondingly, the LMF receives the parameters of variational probability distribution #2 and configuration information #5 from the UE.

[0487] Among them, the parameters of variational probability distribution #2 and the content and interpretation of configuration information #5, as well as the specific implementation method can refer to the relevant description of step S1130 of the above method 1100.

[0488] S1690, LMF determines the location of the UE based on the parameters of variational probability distribution #2 and configuration information #5.

[0489] For the specific implementation method, please refer to the relevant description of step S1140 of the above method 1100.

[0490] In the embodiment of the present application, taking the generation model as VAE as an example, the UE measures the measurement quantity of the PRS and obtains the measurement result of the measurement quantity. Furthermore, the UE and LMF align the configuration parameters of VAE2 by sending configuration information #5, so that the fitted / trained VAE2 used for UE positioning is the same, thereby ensuring that the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the VAE2 is more accurate, thereby improving the positioning accuracy of the UE.

[0491] Figure 17 is a flow chart of a communication method 1700 provided in an embodiment of the present application. As shown in Figure 17, taking LMF as a core network element, UE#1 as the first device, and UE#2 as the second device as an example, model training / fitting in this implementation occurs on the UE#1 side, and model inference / use occurs on the LMF side. It should be understood that the relevant descriptions in the embodiments shown in Figures 10 and 11 above are also applicable to this implementation, and the same or similar technical means may exist between Figures 10, 11, and 17. The contents described in the embodiments shown in Figures 17 and 10 and 11 will not be repeated here.

[0492] It should be understood that this implementation method takes the generation model as VAE as an example, and UE#1 obtains the measurement result of the measurement quantity by measuring the SL-PRS. Furthermore, UE#1 determines VAE3 based on the configuration information #6 sent by the LMF, and uses VAE3 to process the channel measurement result to obtain the variational probability distribution (corresponding to method one), or, UE#1 reports the configuration information #6 and the parameters of the variational probability distribution to the LMF (corresponding to method two), so that UE#1 and LMF align the configuration information #6, ensuring that the VAE3 used for fitting / training of UE positioning is the same, thereby ensuring that the analysis and application of the probability distribution of the measurement result of the measurement quantity based on the VAE3 is more accurate, thereby improving the positioning accuracy of the UE.

[0493] Method 1:

[0494] S1710, LMF sends configuration information #6 to UE#1, and correspondingly, UE#1 receives configuration information #6 from LMF.

[0495] The content, meaning, and specific implementation of configuration information #6 may refer to the description of step S1010 of the above method 1000 .

[0496] S1720, UE#2 sends SL-PRS to UE#1, and correspondingly, UE#1 receives SL-PRS from UE#2.

[0497] S1730 , UE# 1 determines variational probability distribution # 3 of the measurement quantity used for UE positioning according to measurement result # 6 and configuration information # 6 .

[0498] For example, UE#1 measures SL-PRS to obtain channel measurement result #6, and can determine VAE3 based on measurement result #6, and use the channel measurement result #6 as the input of VAE3, and the output of VAE3 is variational probability distribution #3.

[0499] For details on the content and meaning of the measurement quantity, the correlation between the measurement quantity and the channel measurement result #6, and the specific implementation method, please refer to the relevant description of step S1020 of the above method 1000.

[0500] S1740, UE#1 sends the parameters of variational probability distribution #3 to LMF, and LMF receives the parameters of variational probability distribution #3 from UE#1.

[0501] The contents and definitions of the parameters of variational probability distribution #3, as well as their specific implementation methods, can be found in the description of step S1030 of the above method 1000.

[0502] S1750, LMF determines the location of the UE based on configuration information #6 and parameters of variational probability distribution #3.

[0503] For the specific implementation, please refer to the relevant description of step S1040 of the above method 1000.

[0504] Method 2:

[0505] S1760, UE#2 sends SL-PRS to UE#1, and correspondingly, UE#1 receives SL-PRS from UE#2.

[0506] S1770, UE#1 determines variational probability distribution #3 of the measurement quantity used for UE positioning according to channel measurement result #6.

[0507] Exemplarily, UE#1 measures the SL-PRS to obtain measurement result #6, and uses the channel measurement result #6 as the input of VAE3. The output of VAE3 is variational probability distribution #3.

[0508] For the content and meaning of the measurement amount, the correlation between the measurement amount and the channel measurement result #6, and the specific implementation method, please refer to the relevant description of step S1120 of the above method 1100.

[0509] S1780, UE#1 sends the parameters of variational probability distribution #3 and configuration information #6 to LMF. Correspondingly, LMF receives the parameters of variational probability distribution #3 and configuration information #6 from UE#1.

[0510] Among them, the parameters of variational probability distribution #3 and the content and interpretation of configuration information #6, as well as the specific implementation method can refer to the relevant description of step S1130 of the above method 1100.

[0511] S1790, LMF determines the UE's location based on the parameters of variational probability distribution #3 and configuration information #6.

[0512] For the specific implementation method, please refer to the relevant description of step S1140 of the above method 1100.

[0513] In this embodiment of the present application, using a VAE as the generation model, UE#1 measures the SL-PRS measurement quantity to obtain a measurement result of the measurement quantity. Furthermore, UE#1 and the LMF align the configuration parameters of VAE3 by sending configuration information #6, so that the fitted / trained VAE3 used for UE positioning is the same. This ensures that the analysis and application of the probability distribution of the measurement result of the measurement quantity based on VAE3 is more accurate, thereby improving the UE's positioning accuracy.

[0514] It should be noted that the method shown in Figures 15 to 17 above utilizes a measurement result distribution fitting method based on VAE. Optionally, the technical solution of the present application is also applicable to a measurement result distribution fitting method based on GAN. For specific implementation methods, please refer to the relevant descriptions of Figures 15 to 17 above. For the sake of brevity, no further explanation will be given.

[0515] The method provided in the embodiments of the present application is described in detail above with reference to Figures 1 to 17 . Below, the apparatus provided in the embodiments of the present application is described in detail with reference to Figures 17 to 18 . It should be understood that the description of the apparatus embodiment corresponds to the description of the method embodiment. Therefore, for matters not described in detail, reference can be made to the method embodiment above, and for the sake of brevity, they will not be repeated here.

[0516] Figure 18 is a schematic diagram of a communication device 1800 provided in an embodiment of the present application. As shown in Figure 18, the communication device 1800 includes a processing module 1801 and a communication module 1802. The communication device 1800 can be a first device (such as an access network device or a terminal device), or it can be a communication device applied to the first device or used in combination with the first device and capable of implementing the method executed by the first device, such as a chip, a chip system or a circuit. Alternatively, the communication device 1800 can be a core network network element (such as a location management function network element), or it can be a communication device applied to the core network network element or used in combination with the core network network element and capable of implementing the method executed by the core network network element, such as a chip, a chip system or a circuit.

[0517] The communication module may also be referred to as a transceiver module, transceiver, transceiver, or transceiver device. The processing module may also be referred to as a processor, processing board, processing unit, or processing device. Optionally, the communication module is used to perform the sending and receiving operations of the first device (e.g., access network device or terminal device) or core network element (e.g., location management function element) in the above method. The device used to implement the receiving function in the communication module can be regarded as the receiving unit, and the device used to implement the sending function in the communication module can be regarded as the sending unit. That is, the communication module includes a receiving unit and a sending unit.

[0518] When the communication device 1800 is applied to the first device, the processing module 1801 can be used to implement the processing function of the first device (such as an access network device or a terminal device) in the above embodiments, and the communication module 1802 can be used to implement the transceiver function of the first device in the above embodiments.

[0519] When the communication device 1800 is applied to a core network element, the processing module 1801 can be used to implement the processing function of the core network element (such as the location management function element) in the above embodiments, and the communication module 1802 can be used to implement the receiving and sending function of the first device in the above embodiments.

[0520] In addition, it should be noted that the aforementioned communication module and / or processing module can be implemented by a virtual module, for example, the processing module can be implemented by a software functional unit or a virtual device, and the communication module can be implemented by a software function or a virtual device. Alternatively, the processing module or the communication module can also be implemented by a physical device, for example, if the device is implemented using a chip / circuit (such as an integrated circuit or a logic circuit, etc.). The communication module can be an input and output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operations) and output operations (corresponding to the aforementioned sending operations); the processing module is an integrated processor or microprocessor or circuit (such as an integrated circuit or a logic circuit, etc.).

[0521] The division of modules in this application is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the examples of this application may be integrated into a single processor, exist physically as separate modules, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in either hardware or software functional modules.

[0522] Figure 19 is a schematic diagram of another communication device 1900 provided in an embodiment of the present application. As shown in Figure 19, communication device 1900 can optionally be the aforementioned first device or core network element, or a chip or chip system for the aforementioned first device or core network element. Optionally, the chip system in this application can be composed of a chip, or can also include a chip and other discrete devices.

[0523] The communication device 1900 can be used to implement the functions of any network element (for example, a core network element or a first device) in the communication system described in the above examples. Optionally, the core network element is a location management function element, and the first device is an access network device or a terminal device. The communication device 1900 may include a processing circuit 1910. Optionally, the processing circuit 1910 is coupled to a memory, and the memory may be located within the device, or the memory may be integrated with the processor, or the memory may be located outside the device. For example, the communication device 1900 may further include at least one memory 1920. The memory 1920 stores the necessary computer programs, computer programs or instructions and / or data for implementing any of the above examples; the processing circuit 1910 may execute the computer program stored in the memory 1920 to complete the method in any of the above examples.

[0524] The communication device 1900 may also include a transceiver circuit 1930, and the communication device 1900 can exchange information with other devices through the transceiver circuit 1930. Exemplarily, the transceiver circuit 1930 can be a transceiver, circuit, bus, module, pin or other type of communication interface. When the communication device 1900 is a chip-type device or circuit, the transceiver circuit 1930 in the device 1900 can also be an input-output circuit, or an interface circuit, which can input information (or receive information) and output information (or send information). When the communication device 1900 is a core network element, a network device or a terminal device, the transceiver circuit can be a transmitter, a receiver or a transceiver, or a communication interface, which is not limited here.

[0525] The processing circuit 1910 may be one or more processors, or all or part of the processing circuits in one or more processors. The processing circuit 1910 may be an integrated processor, microprocessor, integrated circuit, or logic circuit, and the processor may determine output information based on input information.

[0526] Coupling in this application refers to an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, and is used for information exchange between devices, units, or modules. Processing circuit 1910 may operate in conjunction with memory 1920 and transceiver circuit 1930. This application does not limit the specific connection medium between the processing circuit 1910, memory 1920, and transceiver circuit 1930.

[0527] Optionally, as shown in FIG19 , the processing circuit 1910, the memory 1920, and the transceiver circuit 1930 are interconnected via a bus 1940. Optionally, the bus may include an address bus, a data bus, a control bus, or other types of buses. Furthermore, for ease of illustration, FIG19 shows one bus 1940, but this does not mean that there is only one bus or only one type of bus.

[0528] It should be understood that the processors mentioned in the embodiments of the present application may be the following devices or the circuit portions of the following devices used for processing functions: a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0529] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0530] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) can be integrated into the processor.

[0531] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0532] In an embodiment of the present application, the method described in the above embodiment can be executed by the first device and the core network network element, or can be executed by the chip, chip system or circuit of the first device and the core network network element, and the chip, chip system or circuit can be installed in the first device and the core network network element.

[0533] An embodiment of the present application provides a computer-readable storage medium storing computer instructions for implementing the methods executed by a device (such as a first device, or a core network element) in the above-mentioned method embodiments.

[0534] For example, when the computer program is executed by a computer, the computer can implement the methods performed by the device (such as the first device, or a core network element, etc.) in each embodiment of the above method.

[0535] An embodiment of the present application provides a computer program product comprising instructions, which, when executed by a computer, implement the methods performed by a device (such as a first device, or a core network element (or a positioning device), etc.) in the above-mentioned method embodiments.

[0536] An embodiment of the present application provides a communication system, which includes the first device and / or core network element in each of the above embodiments. For example, the system includes the first device and / or core network element in the above embodiments. For another example, the system includes the first device and / or core network element in the above embodiments.

[0537] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0538] To facilitate understanding of the above embodiments provided in this application, the following points are explained:

[0539] In this application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0540] In the present application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In the text description of the present application, the character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b and c can mean: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c. Wherein a, b and c can be single or multiple, respectively.

[0541] In this application, the terms "first," "second," and various numerical references are used for descriptive purposes only and are not intended to limit the scope of the embodiments of this application. For example, they are used to distinguish between different messages, rather than to describe a specific order or precedence. It should be understood that the terms described in this manner are interchangeable, where appropriate, to allow for the description of scenarios beyond the embodiments of this application.

[0542] In this application, the terms "comprises" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, product or apparatus.

[0543] In this application, "used for indication" can include direct indication and indirect indication. When describing a certain indication information as indicating A, it can include whether the indication information directly indicates A or indirectly indicates A, and it does not necessarily mean that the indication information carries A. Direct indication of information A means including information A; implicit indication of information A means indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0544] It can be understood that some optional features in the various embodiments of the present application may not depend on other features in certain scenarios, and may also be combined with other features in certain scenarios, without limitation.

[0545] It can also be understood that in some of the above embodiments, sending information is mentioned multiple times. For example, "network element A sends information A to network element B", which can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, and can include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, and can include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be repeated here.

[0546] It can also be understood that in some of the above embodiments, the AI ​​model is mainly used as an example for illustrative description. It can be understood that the above AI model can also be used for other purposes.

[0547] It can also be understood that the solutions in the various embodiments of the present application can be reasonably combined and used, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained with each other in the various embodiments, without limitation to this.

[0548] It can also be understood that in the above-mentioned various method embodiments, the methods and operations implemented by the first device or positioning device can also be implemented by components (such as chips or circuits) that can be implemented by the first device or positioning device, without limitation.

[0549] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0550] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0551] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0552] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0553] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0554] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0555] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: The method is performed by a first device or a chip or circuit of the first device, and includes: Receiving configuration information from a core network element, where the configuration information is used to indicate configuration parameters of a generated model; The channel measurement result is processed using a first model to obtain a probability distribution of a measurement result of a measurement quantity used for terminal device positioning, the first model is determined based on a configuration parameter of the generation model, and the measurement quantity corresponds to the channel measurement result.

2. The method according to claim 1, characterized in that The method further comprises: Sending first information to the core network element, where the first information is used to indicate the probability distribution.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: The type of the generative model and / or the function of the generative model are obtained.

4. The method according to any one of claims 1 to 3, characterized in that The channel measurement result is based on measurement of a reference signal.

5. The method according to any one of claims 1 to 4, characterized in that The generative model is any of the following: Gaussian mixture models; Variational Autoencoder; Generative Adversarial Networks.

6. The method according to any one of claims 1 to 5, characterized in that The generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: A method for generating the Gaussian mixture model; A convergence threshold of the Gaussian mixture model; The maximum number of iterations of the Gaussian mixture model; Model parameters of the Gaussian mixture model; The maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; The Gaussian mixture model includes a maximum value N of the expected value of a single Gaussian model, where N is a positive number; The maximum value A of the variance or covariance of the single Gaussian model included in the Gaussian mixture model, where A is a positive number; The Gaussian mixture model includes one or more single Gaussian models in the Gaussian mixture model.

7. The method according to any one of claims 1 to 6, characterized in that The generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: Structural parameters of the variational autoencoder; The type of neural network used by the variational autoencoder; The number of neural network layers used by the variational autoencoder; The number of neurons contained in the neural network used by the variational autoencoder; The input and / or output dimensions of the variational autoencoder; The values ​​of the model parameters of the variational autoencoder.

8. The method according to any one of claims 1 to 7, characterized in that The measurements include one or more of the following: Reference signal time difference RSTD; Time difference of arrival TDoA; Time of arrival ToA; Angle of arrival AoA; Line-of-sight LoS probability.

9. The method according to any one of claims 2 to 8, characterized in that The generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: The values ​​of k expected values; k variance or covariance values; The proportion of the k single Gaussian models in the Gaussian mixture model; The k expected values, the k variances or covariances correspond one-to-one to the k single Gaussian models.

10. The method according to any one of claims 2 to 9, characterized in that The generative model is a variational autoencoder, and the first information includes one or more of the following: The values ​​of the model parameters of the variational autoencoder; The value of the probability distribution output by the variational autoencoder.

11. The method according to any one of claims 1 to 10, characterized in that The channel measurement result is based on the measurement of the reference signal, including any one of the following: The first device is an access network device, and the channel measurement result is obtained based on a first channel measurement, wherein the first channel measurement includes: measuring a sounding reference signal from a terminal device; or The first device is a terminal device, the channel measurement result is obtained based on a second channel measurement, and the second channel measurement includes: measuring a positioning reference signal or a channel state information reference signal from an access network device; or, The first device is a first terminal device, and the channel measurement result is obtained based on a third channel measurement, and the third channel measurement includes: measuring a side positioning reference signal from a second terminal device.

12. The method according to any one of claims 1 to 11, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, The configuration information is used to indicate the first configuration parameter, and the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

13. The method according to any one of claims 1 to 12, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, and the receiving of configuration information from a core network element includes: Receiving the configuration information from the core network element through first signaling; The configuration information of the first configuration parameter is carried in the first part of the first signaling, and the configuration information of the second configuration parameter is carried in the second part of the first signaling.

14. The method according to claim 13, characterized in that Receiving configuration information from the core network element through the first signaling includes: receiving the first configuration parameter from the core network element through the first part of the first signaling at a first moment, and, Receiving the second configuration parameter from the core network element through the second part of the first signaling at a second moment; The first moment and the second moment are the same, or the first moment and the second moment are different.

15. A communication method, characterized in that: The method is performed by a core network element or a chip or circuit of a core network element, and includes: Sending configuration information to the first device, where the configuration information is used to indicate configuration parameters of the generated model; First information is received from the first device, where the first information indicates a probability distribution of a measurement result of a measurement quantity used for positioning of a terminal device, and the probability distribution is related to a configuration parameter of the generation model.

16. The method according to claim 15, characterized in that The method further comprises: The location of the terminal device is determined according to the probability distribution of the measurement result of the measurement quantity and the configuration parameters of the generation model.

17. The method according to claim 15 or 16, characterized in that The generative model is any of the following: Gaussian mixture models; Variational Autoencoder; Generative Adversarial Networks.

18. The method according to any one of claims 15 to 17, characterized in that The generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: A method for generating the Gaussian mixture model; A convergence threshold of the Gaussian mixture model; The maximum number of iterations of the Gaussian mixture model; Model parameters of the Gaussian mixture model; The maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; The Gaussian mixture model includes a maximum value N of the expected value of a single Gaussian model, where N is a positive number; The maximum value A of the variance or covariance of the single Gaussian model included in the Gaussian mixture model, where A is a positive number; The Gaussian mixture model includes one or more single Gaussian models in the Gaussian mixture model.

19. The method according to any one of claims 15 to 18, characterized in that The generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: Structural parameters of the variational autoencoder; The type of neural network used by the variational autoencoder; The number of neural network layers used by the variational autoencoder; The number of neurons contained in the neural network used by the variational autoencoder; The input and / or output dimensions of the variational autoencoder; The values ​​of the model parameters of the variational autoencoder.

20. The method according to any one of claims 15 to 19, characterized in that The measurements include one or more of the following: Reference signal time difference RSTD; Time difference of arrival TDoA; Time of arrival ToA; Angle of arrival AoA; Line-of-sight LoS probability.

21. The method according to any one of claims 15 to 20, characterized in that The generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: The values ​​of k expected values; k variance or covariance values; The proportion of the k single Gaussian models in the Gaussian mixture model; The k expected values, the k variances or covariances correspond one-to-one to the k single Gaussian models.

22. The method according to any one of claims 15 to 21, characterized in that The generative model is a variational autoencoder, and the first information includes one or more of the following: The values ​​of the model parameters of the variational autoencoder; The value of the probability distribution output by the variational autoencoder.

23. The method according to any one of claims 15 to 22, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, The configuration information is used to indicate the first configuration parameter, and the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

24. The method according to any one of claims 15 to 23, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, and sending the configuration information to the first device includes: Sending the configuration information to the first device through a first signaling; The configuration information of the first configuration parameter is carried in the first part of the first signaling, and the configuration information of the second configuration parameter is carried in the second part of the first signaling.

25. The method according to claim 24, characterized in that Sending the configuration information to the first device through a first signaling includes: sending the first configuration parameter to the first device through a first part of the first signaling at a first moment, and, Sending the second configuration parameter to the first device through the second part of the first signaling at a second moment; The first moment and the second moment are the same, or the first moment and the second moment are different.

26. A communication method, characterized in that: The method is performed by a first device or a chip or circuit of the first device, and includes: Acquire configuration information, where the configuration information is used to indicate configuration parameters of the generated model; The channel measurement result is processed using a first model to obtain a probability distribution of a measurement result of a measurement quantity used for terminal device positioning, the first model is determined based on a configuration parameter of the generation model, and the measurement quantity corresponds to the channel measurement result.

27. The method according to claim 26, characterized in that The method further comprises: Sending first information and all or part of the configuration information to a core network element, wherein the first information is used to indicate the probability distribution.

28. The method according to claim 26 or 27, characterized in that The channel measurement result is based on measurement of a reference signal.

29. The method according to any one of claims 26 to 28, characterized in that The generative model is any of the following: Gaussian mixture models; Variational Autoencoder; Generative Adversarial Networks.

30. The method according to any one of claims 26 to 29, characterized in that The generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: A method for generating the Gaussian mixture model; A convergence threshold of the Gaussian mixture model; The maximum number of iterations of the Gaussian mixture model; Model parameters of the Gaussian mixture model; The maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; The Gaussian mixture model includes a maximum value N of the expected value of a single Gaussian model, where N is a positive number; The maximum value A of the variance or covariance of the single Gaussian model included in the Gaussian mixture model, where A is a positive number; The Gaussian mixture model includes one or more single Gaussian models in the Gaussian mixture model.

31. The method according to any one of claims 26 to 30, characterized in that The generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: Structural parameters of the variational autoencoder; The type of neural network used by the variational autoencoder; The number of neural network layers used by the variational autoencoder; The number of neurons contained in the neural network used by the variational autoencoder; The input and / or output dimensions of the variational autoencoder; The values ​​of the model parameters of the variational autoencoder.

32. The method according to any one of claims 26 to 31, characterized in that The measurements include one or more of the following: Reference signal time difference RSTD; Time difference of arrival TDoA; Time of arrival ToA; Angle of arrival AoA; Line-of-sight LoS probability.

33. The method according to claim 27 or 32, characterized in that The generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: The values ​​of k expected values; k variance or covariance values; The proportion of the k single Gaussian models in the Gaussian mixture model; The k expected values, the k variances or covariances correspond one-to-one to the k single Gaussian models.

34. The method according to any one of claims 27 to 33, characterized in that The generative model is a variational autoencoder, and the first information includes one or more of the following: The values ​​of the model parameters of the variational autoencoder; The value of the probability distribution output by the variational autoencoder.

35. The method according to any one of claims 26 to 34, characterized in that The channel measurement result is based on the measurement of the reference signal, including any one of the following: The first device is an access network device, and the channel measurement result is obtained based on a first channel measurement, wherein the first channel measurement includes: measuring a sounding reference signal from a terminal device; or The first device is a terminal device, the channel measurement result is obtained based on a second channel measurement, and the second channel measurement includes: measuring a positioning reference signal or a channel state information reference signal from an access network device; or, The first device is a first terminal device, and the channel measurement result is obtained based on a third channel measurement, and the third channel measurement includes: measuring a side positioning reference signal from a second terminal device.

36. The method according to any one of claims 26 to 35, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, The configuration information is used to indicate the first configuration parameter, and the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

37. The method according to any one of claims 26 to 36, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, and the acquiring configuration information includes: Acquiring the configuration information through a first signaling; The configuration information of the first configuration parameter is carried in the first part of the first signaling, and the configuration information of the second configuration parameter is carried in the second part of the first signaling.

38. The method according to claim 37, characterized in that Acquiring configuration information through the first signaling includes: acquiring the first configuration parameter through the first part of the first signaling at a first moment, and, Acquire the second configuration parameter through the second part of the first signaling at a second moment; The first moment and the second moment are the same, or the first moment and the second moment are different.

39. A communication method, characterized in that: The method is performed by a core network element or a chip or circuit of a core network element, and includes: Receive all or part of first information and configuration information from a first device, wherein the first information indicates a probability distribution of measurement results of a measurement quantity used for positioning a terminal device, and the configuration information is used to indicate configuration parameters of a generation model, and the probability distribution of the measurement results of the measurement quantity is related to the configuration parameters of the generation model.

40. The method according to claim 39, characterized in that The method further comprises: The location of the terminal device is determined according to the probability distribution of the measurement result of the measurement quantity and the configuration parameters of the generation model.

41. The method according to claim 39 or 40, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, The configuration information is used to indicate the first configuration parameter, and the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

42. The method according to any one of claims 39 to 41, characterized in that The generative model is any of the following: Gaussian mixture models; Variational Autoencoder; Generative Adversarial Networks.

43. The method according to any one of claims 39 to 42, characterized in that The generation model is a Gaussian mixture model, and the configuration parameters of the generation model include one or more of the following: A method for generating the Gaussian mixture model; A convergence threshold of the Gaussian mixture model; The maximum number of iterations of the Gaussian mixture model; Model parameters of the Gaussian mixture model; The maximum number M of single Gaussian models included in the Gaussian mixture model, where M is a positive integer; The Gaussian mixture model includes a maximum value N of the expected value of a single Gaussian model, where N is a positive number; The maximum value A of the variance or covariance of the single Gaussian model included in the Gaussian mixture model, where A is a positive number; The Gaussian mixture model includes one or more single Gaussian models in the Gaussian mixture model.

44. The method according to any one of claims 39 to 43, characterized in that The generative model is a variational autoencoder, and the configuration parameters of the generative model include one or more of the following: Structural parameters of the variational autoencoder; The type of neural network used by the variational autoencoder; The number of neural network layers used by the variational autoencoder; The number of neurons contained in the neural network used by the variational autoencoder; The input and / or output dimensions of the variational autoencoder; The values ​​of the model parameters of the variational autoencoder.

45. The method according to any one of claims 39 to 44, characterized in that The measurements include one or more of the following: Reference signal time difference RSTD; Time difference of arrival TDoA; Time of arrival ToA; Angle of arrival AoA; Line-of-sight LoS probability.

46. ​​The method according to any one of claims 39 to 45, characterized in that The generation model is a Gaussian mixture model, the Gaussian mixture model includes k single Gaussian models, k is an integer greater than or equal to 1, and the first information includes one or more of the following: The values ​​of k expected values; k variance or covariance values; The proportion of the k single Gaussian models in the Gaussian mixture model; The k expected values, the k variances or covariances correspond one-to-one to the k single Gaussian models.

47. The method according to any one of claims 39 to 46, characterized in that The generative model is a variational autoencoder, and the first information includes one or more of the following: The values ​​of the model parameters of the variational autoencoder; The value of the probability distribution output by the variational autoencoder.

48. The method according to any one of claims 39 to 47, characterized in that The configuration parameters include a first configuration parameter and a second configuration parameter, wherein the configuration information is used to indicate the first configuration parameter and the second configuration parameter; or, The configuration information is used to indicate the first configuration parameter, and the second configuration parameter is determined according to a mapping relationship, and the mapping relationship is used to indicate a corresponding relationship between the first configuration parameter and the second configuration parameter.

49. A communication device, characterized in that: Comprising a module for executing the method of any one of claims 1-14, or 26-38, or comprising a module for executing the method of any one of claims 15-25, or 39-48.

50. A communication device, characterized in that: The method comprises at least one processor configured to execute a computer program or instruction in a memory so that the method according to any one of claims 1 to 14 or 26 to 38 is executed, or the method according to any one of claims 15 to 25 or 39 to 48 is executed.

51. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is run on a computer, the method according to any one of claims 1 to 48 is executed.

52. A computer program product, characterized in that The method comprises a computer program or instructions, which, when executed by a processor, causes the method according to any one of claims 1 to 48 to be performed.

Images